Arrow Research search

Author name cluster

Jakob Foerster

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

53 papers
1 author row

Possible papers

53

NeurIPS Conference 2025 Conference Paper

A Clean Slate for Offline Reinforcement Learning

  • Matthew Jackson
  • Uljad Berdica
  • Jarek Liesen
  • Shimon Whiteson
  • Jakob Foerster

Progress in offline reinforcement learning (RL) has been impeded by ambiguous problem definitions and entangled algorithmic designs, resulting in inconsistent implementations, insufficient ablations, and unfair evaluations. Although offline RL explicitly avoids environment interaction, prior methods frequently employ extensive, undocumented online evaluation for hyperparameter tuning, complicating method comparisons. Moreover, existing reference implementations differ significantly in boilerplate code, obscuring their core algorithmic contributions. We address these challenges by first introducing a rigorous taxonomy and a transparent evaluation protocol that explicitly quantifies online tuning budgets. To resolve opaque algorithmic design, we provide clean, minimalistic, single-file implementations of various model-free and model-based offline RL methods, significantly enhancing clarity and achieving substantial speed-ups. Leveraging these streamlined implementations, we propose Unifloral, a unified algorithm that encapsulates diverse prior approaches and enables development within a single, comprehensive hyperparameter space. Using Unifloral with our rigorous evaluation protocol, we develop two novel algorithms - TD3-AWR (model-free) and MoBRAC (model-based) - which substantially outperform established baselines. Our implementation is publicly available at https: //github. com/EmptyJackson/unifloral.

PDF Details

NeurIPS Conference 2025 Conference Paper

AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement

  • J Rosser
  • Jakob Foerster

Scaffolding Large Language Models (LLMs) into multi-agent systems often improves performance on complex tasks, but the safety impact of such scaffolds has not been thoroughly explored. We introduce AgentBreeder, a framework for multi-objective self-improving evolutionary search over scaffolds. We evaluate discovered scaffolds on widely recognized reasoning, mathematics, and safety benchmarks and compare them with popular baselines. In "blue" mode, we see a 79. 4% average uplift in safety benchmark performance while maintaining or improving capability scores. In "red" mode, we find adversarially weak scaffolds emerging concurrently with capability optimization. Our work demonstrates the risks of multi-agent scaffolding and provides a framework for mitigating them. Code is available at \url{https: //github. com/jrosseruk/AgentBreeder}.

PDF Details

NeurIPS Conference 2025 Conference Paper

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench

  • Edan Toledo
  • Karen Hambardzumyan
  • Martin Josifoski
  • Rishi Hazra
  • Nicolas Baldwin
  • Alexis Audran-Reiss
  • Michael Kuchnik
  • Despoina Magka

AI research agents are demonstrating great potential to accelerate scientific progress by automating the design, implementation, and training of machine learning models. We focus on methods for improving agents' performance on MLE-bench, a challenging benchmark where agents compete in Kaggle competitions to solve real-world machine learning problems. We formalize AI research agents as search policies that navigate a space of candidate solutions, iteratively modifying them using operators. By designing and systematically varying different operator sets and search policies (Greedy, MCTS, Evolutionary), we show that their interplay is critical for achieving high performance. Our best pairing of search strategy and operator set achieves a state-of-the-art result on MLE-bench lite, increasing the success rate of achieving a Kaggle medal from 39. 6% to 47. 7%. Our investigation underscores the importance of jointly considering the search strategy, operator design, and evaluation methodology in advancing automated machine learning.

PDF Details

IJCAI Conference 2025 Conference Paper

Combining Code Generating Large Language Models and Self-Play to Iteratively Refine Strategies in Games

  • Yoram Bachrach
  • Edan Toledo
  • Karen Hambardzumyan
  • Despoina Magka
  • Martin Josifoski
  • Minqi Jiang
  • Jakob Foerster
  • Roberta Raileanu

We propose a self-play approach to generating strategies for playing in multi-player games, where strategies are represented as computer code. We use large language models (LLMs) to generate pieces of code to play in the game, which we refer to as generated bots. We engage the LLM generated bots in competitions, designed to generate increasingly stronger strategies. We follow game theoretic principles in organizing these tournaments, and use a Policy Space Response Oracle (PSRO) approach. We start with an initial set of LLM generated bots, and continue in rounds for adding new bots into the population. Each round adds a bot to the population by asking the LLM to produce code for playing against a bot representing the Nash equilibrium mixture over the current population. Our analysis shows that even a few rounds are sufficient to produces strong bots for playing the game. Our demo shows the process for the game of Checkers. We allow users to select initial bots in the population, run the process, inspect how the bots evolve over time, and play against the generated bots.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Imagined Autocurricula

  • Ahmet Hamdi Güzel
  • Matthew Jackson
  • Jarek Liesen
  • Tim Rocktäschel
  • Jakob Foerster
  • Ilija Bogunovic
  • Jack Parker-Holder

Training agents to act in embodied environments typically requires vast training data or access to accurate simulation, neither of which exists for many cases in the real world. Instead, world models are emerging as an alternative–leveraging offline, passively collected data, they make it possible to generate diverse worlds for training agents in simulation. In this work, we harness world models to generate “imagined” environments to train robust agents capable of generalizing to novel task variations. One of the challenges in doing this is ensuring the agent trains on useful generated data. We thus propose a novel approach IMAC (Imagined Autocurricula) leveraging Unsupervised Environment Design (UED), induces an automatic curriculum over generated worlds. In a series of challenging, procedurally generated environments, we show it is possible to achieve strong transfer performance on held-out environments having trained only inside a world model learned from a narrower dataset. We believe this opens the path to utilizing larger-scale, foundation world models for generally capable agents.

PDF Details

NeurIPS Conference 2025 Conference Paper

Improving Regret Approximation for Unsupervised Dynamic Environment Generation

  • Harry Mead
  • Bruno Lacerda
  • Jakob Foerster
  • Nick Hawes

Unsupervised Environment Design (UED) seeks to automatically generate training curricula for reinforcement learning (RL) agents, with the goal of improving generalisation and zero-shot performance. However, designing effective curricula remains a difficult problem, particularly in settings where small subsets of environment parameterisations result in significant increases in the complexity of the required policy. Current methods struggle with a difficult credit assignment problem and rely on regret approximations that fail to identify challenging levels, both of which are compounded as the size of the environment grows. We propose Dynamic Environment Generation for UED (DEGen) to enable a denser level generator reward signal, reducing the difficulty of credit assignment and allowing for UED to scale to larger environment sizes. We also introduce a new regret approximation, Maximised Negative Advantage (MNA), as a significantly improved metric to optimise for, that better identifies more challenging levels. We show empirically that MNA outperforms current regret approximations and when combined with DEGen, consistently outperforms existing methods, especially as the size of the environment grows. We have made all our code available here: \url{https: //github. com/HarryMJMead/Dynamic-Environment-Generation-for-UED}.

PDF Details

NeurIPS Conference 2025 Conference Paper

LILO: Learning to Reason at the Frontier of Learnability

  • Thomas Foster
  • Anya Sims
  • Johannes Forkel
  • Jakob Foerster

Reinforcement learning is widely adopted in post-training large language models, especially for reasoning-style tasks such as maths questions. However, as we show, most existing methods will provably fail to learn from questions that are too hard, where the model always fails, or too easy, where the model always succeeds. Much human effort is therefore spent continually producing datasets of questions of a suitable difficulty for state-of-the-art models. Given this, we consider how to algorithmically identify questions that allow for maximally efficient training. We introduce a method, LILO (Learnability Improves LLMs Optimally), that prioritises training on questions with high variance of success, known as learnability, and we provide theory proving LILO maximises the expected improvement of the model. We run a wide range of experiments over multiple base models, algorithms and reasoning datasets to demonstrate that LILO consistently improves final test accuracy and can yield a 3x reduction in the number of training steps required to reach it. We explore how questions with high learnability can be efficiently identified, and discuss how learnability can be scaled to produce LLM agents that autonomously and open-endedly expand the frontier of human knowledge.

PDF Details

NeurIPS Conference 2025 Conference Paper

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

  • Andrew M. Bean
  • Ryan Othniel Kearns
  • Angelika Romanou
  • Franziska Sofia Hafner
  • Harry Mayne
  • Jan Batzner
  • Negar Foroutan Eghlidi
  • Chris Schmitz

Evaluating large language models (LLMs) is crucial for both assessing their capabilities and identifying safety or robustness issues prior to deployment. Reliably measuring abstract and complex phenomena such as safety' and robustness' requires strong construct validity, that is, having measures that represent what matters to the phenomenon. With a team of 29 expert reviewers, we conduct a systematic review of 445 LLM benchmarks from leading conferences in natural language processing and machine learning. Across the reviewed articles, we find patterns related to the measured phenomena, tasks, and scoring metrics which undermine the validity of the resulting claims. To address these shortcomings, we provide eight key recommendations and detailed actionable guidance to researchers and practitioners in developing LLM benchmarks.

PDF Details

NeurIPS Conference 2025 Conference Paper

Meta-Learning Objectives for Preference Optimization

  • Carlo Alfano
  • Silvia Sapora
  • Jakob Foerster
  • Patrick Rebeschini
  • Yee Whye Teh

Evaluating preference optimization (PO) algorithms on LLM alignment is a challenging task that presents prohibitive costs, noise, and several variables like model size and hyper-parameters. In this work, we show that it is possible to gain insights on the efficacy of PO algorithm on simpler benchmarks. We design a diagnostic suite of MuJoCo tasks and datasets, which we use to systematically evaluate PO algorithms, establishing a more controlled and cheaper benchmark. We then propose a novel family of PO algorithms based on mirror descent, which we call Mirror Preference Optimization (MPO). Through evolutionary strategies, we search this class to discover algorithms specialized to specific properties of preference datasets, such as mixed-quality or noisy data. We demonstrate that our discovered PO algorithms outperform all known algorithms in the targeted MuJoCo settings. Finally, based on the insights gained from our MuJoCo experiments, we design a PO algorithm that significantly outperform existing baselines in an LLM alignment task.

PDF Details

NeurIPS Conference 2025 Conference Paper

The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements

  • Bingchen Zhao
  • Despoina Magka
  • Minqi Jiang
  • Xian Li
  • Roberta Raileanu
  • Tatiana Shavrina
  • Jean-Christophe Gagnon-Audet
  • Kelvin Niu

Rapidly improving large language models (LLMs) have the potential to assist in scientific progress. One critical skill in this endeavor is the ability to faithfully reproduce existing work. To evaluate the capability of AI agents to reproduce complex code in an active research area, we introduce the Automated LLM Speedrunning Benchmark, leveraging the research community's contributions to the $\textit{NanoGPT speedrun}$, a competition to train a GPT-2 model in the shortest time. Each of the 19 speedrun tasks provides the agent with the previous record's training script, optionally paired with one of three hint formats, ranging from pseudocode to paper-like descriptions of the new record's improvements. Records execute quickly by design and speedrun improvements encompass diverse code-level changes, ranging from high-level algorithmic advancements to hardware-aware optimizations. These features make the benchmark both accessible and realistic for the frontier problem of improving LLM training. We find that recent frontier reasoning LLMs combined with SoTA scaffolds struggle to reimplement already-known innovations in our benchmark, even when given detailed hints. Our benchmark thus provides a simple, non-saturated measure of an LLM's ability to automate scientific reproduction, a necessary (but not sufficient) skill for an autonomous research agent.

PDF Details

AAMAS Conference 2024 Conference Paper

A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem

  • Paul Barde
  • Jakob Foerster
  • Derek Nowrouzezahrai
  • Amy Zhang

Training multiple agents to coordinate is an essential problem with applications in robotics, game theory, economics, and social sciences. However, most existing Multi-Agent Reinforcement Learning (MARL) methods are online and thus impractical for real-world applications in which collecting new interactions is costly or dangerous. While these algorithms should leverage offline data when available, doing so gives rise to what we call the offline coordination problem. Specifically, we identify and formalize the strategy agreement (SA) and the strategy fine-tuning (SFT) coordination challenges, two issues at which current offline MARL algorithms fail. Concretely, we reveal that the prevalent model-free methods are severely deficient and cannot handle coordination-intensive offline multi-agent tasks in either toy or MuJoCo domains. To address this setback, we emphasize the importance of inter-agent interactions and propose the very first model-based offline MARL method. Our resulting algorithm, Model-based Offline Multi-Agent Proximal Policy Optimization (MOMA-PPO) generates synthetic interaction data and enables agents to converge on a strategy while fine-tuning their policies accordingly. This simple model-based solution solves the coordination-intensive offline tasks, significantly outperforming the prevalent model-free methods even under severe partial observability and with learned world models.

PDF

AAMAS Conference 2024 Conference Paper

Analysing the Sample Complexity of Opponent Shaping

  • Kitty Fung
  • Qizhen Zhang
  • Chris Lu
  • Jia Wan
  • Timon Willi
  • Jakob Foerster

Learning in general-sum games often yields collectively sub-optimal results. Addressing this, opponent shaping (OS) methods actively guide the learning processes of other agents, empirically leading to improved individual and group performances in many settings. Early OS methods use higher-order derivatives to shape the learning of co-players, making them unsuitable to shape multiple learning steps. Follow-up work, Model-free Opponent Shaping (M-FOS), addresses these by reframing the OS problem as a meta-game. In contrast to early OS methods, there is little theoretical understanding of the M-FOS framework. Providing theoretical guarantees for M-FOS is hard because A) there is little literature on theoretical sample complexity bounds for meta-reinforcement learning B) M- FOS operates in continuous state and action spaces, so theoretical analysis is challenging. In this work, we present R-FOS, a tabular version of M-FOS that is more suitable for theoretical analysis. R- FOS discretises the continuous meta-game MDP into a tabular MDP. Within this discretised MDP, we adapt the 𝑅𝑚𝑎𝑥 algorithm, most prominently used to derive PAC-bounds for MDPs, as the metalearner in the R-FOS algorithm. We derive a sample complexity bound that is exponential in the cardinality of the inner state and action space and the number of agents. Our bound guarantees that, with high probability, the final policy learned by an R-FOS agent is close to the optimal policy, apart from a constant factor. Finally, we investigate how R-FOS’s sample complexity scales in the size of state-action space. Our theoretical results on scaling are supported empirically in the Matching Pennies environment.

PDF

NeurIPS Conference 2024 Conference Paper

Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning

  • Jonathan Cook
  • Chris Lu
  • Edward Hughes
  • Joel Z. Leibo
  • Jakob Foerster

Cultural accumulation drives the open-ended and diverse progress in capabilities spanning human history. It builds an expanding body of knowledge and skills by combining individual exploration with inter-generational information transmission. Despite its widespread success among humans, the capacity for artificial learning agents to accumulate culture remains under-explored. In particular, approaches to reinforcement learning typically strive for improvements over only a single lifetime. Generational algorithms that do exist fail to capture the open-ended, emergent nature of cultural accumulation, which allows individuals to trade-off innovation and imitation. Building on the previously demonstrated ability for reinforcement learning agents to perform social learning, we find that training setups which balance this with independent learning give rise to cultural accumulation. These accumulating agents outperform those trained for a single lifetime with the same cumulative experience. We explore this accumulation by constructing two models under two distinct notions of a generation: episodic generations, in which accumulation occurs via in-context learning and train-time generations, in which accumulation occurs via in-weights learning. In-context and in-weights cultural accumulation can be interpreted as analogous to knowledge and skill accumulation, respectively. To the best of our knowledge, this work is the first to present general models that achieve emergent cultural accumulation in reinforcement learning, opening up new avenues towards more open-ended learning systems, as well as presenting new opportunities for modelling human culture.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts

  • Qizhen Zhang
  • Nikolas Gritsch
  • Dwaraknath Gnaneshwar
  • Simon Guo
  • David Cairuz
  • Bharat Venkitesh
  • Jakob Foerster
  • Phil Blunsom

Mixture of Experts (MoE) framework has become a popular architecture for large language models due to its superior performance compared to dense models. However, training MoEs from scratch in a large-scale regime is prohibitively expensive. Previous work addresses this challenge by independently training multiple dense expert models and using them to initialize an MoE. In particular, state-of-the-art approaches initialize MoE layers using experts' feed-forward parameters while merging all other parameters, limiting the advantages of the specialized dense models when upcycling them as MoEs. We propose BAM (Branch-Attend-Mix), a simple yet effective improvement to MoE training. BAM makes full use of specialized dense models by not only using their feed-forward network (FFN) to initialize the MoE layers but also leveraging experts' attention weights fully by leveraging them as mixture-of-attention (MoA) layers. We explore two methods for upcycling MoA layers: 1) initializing separate attention experts from dense models including key, value, and query matrices; and 2) initializing only Q projections while sharing key-value pairs across all experts to facilitate efficient inference. Our experiments using seed models ranging from 590 million to 2 billion parameters show that our approach outperforms state-of-the-art approaches under the same data and compute budget in both perplexity and downstream tasks evaluations, confirming the effectiveness of BAM.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Discovering Preference Optimization Algorithms with and for Large Language Models

  • Chris Lu
  • Samuel Holt
  • Claudio Fanconi
  • Alex J. Chan
  • Jakob Foerster
  • Mihaela van der Schaar
  • Robert T. Lange

Offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. Typically, preference optimization is approached as an offline supervised learning task using manually crafted convex loss functions. While these methods are based on theoretical insights, they are inherently constrained by human creativity, so the large search space of possible loss functions remains under-explored. We address this by performing LLM-driven objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (expert) human intervention. Specifically, we iteratively prompt an LLM to propose and implement new preference optimization loss functions based on previously evaluated performance metrics. This process leads to the discovery of previously unknown and performant preference optimization algorithms. The best performing of these we call Discovered Preference Optimization (DiscoPOP), a novel algorithm that adaptively blends logistic and exponential losses. Experiments demonstrate the state-of-the-art performance of DiscoPOP and its successful transfer to held-out tasks.

PDF Details DOI

AAMAS Conference 2024 Conference Paper

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

  • Alexander Rutherford
  • Benjamin Ellis
  • Matteo Gallici
  • Jonathan Cook
  • Andrei Lupu
  • Garðar Ingvarsson
  • Timon Willi
  • Akbir Khan

Benchmarks play an important role in the development of machine learning algorithms, with reinforcement learning (RL) research having been heavily influenced by the available environments. However, RL environments are traditionally run on the CPU, limiting their scalability with typical academic compute. Recent advancements in JAX have enabled the wider use of hardware acceleration to overcome these computational hurdles, enabling massively parallel RL training pipelines and environments. This is particularly useful for multi-agent reinforcement learning (MARL) research. First of all, multiple agents must be considered at each environment step, adding computational burden, and secondly, the sample complexity is increased due to non-stationarity, decentralised partial observability, or other MARL challenges. In this paper, we present JaxMARL, the first open-source code base that combines ease-ofuse with GPU enabled efficiency, and supports a large number of commonly used MARL environments as well as popular baseline algorithms. When considering wall clock time, our experiments Proc. of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024), N. Alechina, V. Dignum, M. Dastani, J. S. Sichman (eds.), May 6 – 10, 2024, Auckland, New Zealand. © 2024 International Foundation for Autonomous Agents and Multiagent Systems (www. ifaamas. org). This work is licenced under the Creative Commons Attribution 4. 0 International (CC-BY 4. 0) licence. show that per-run our JAX-based training pipeline is up to 12500x faster than existing approaches. We also introduce and benchmark SMAX, a vectorised, simplified version of the popular StarCraft Multi-Agent Challenge, which removes the need to run the Star- Craft II game engine. This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL. We provide code at https: //github. com/flairox/jaxmarl.

PDF

NeurIPS Conference 2024 Conference Paper

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

  • Alexander Rutherford
  • Benjamin Ellis
  • Matteo Gallici
  • Jonathan Cook
  • Andrei Lupu
  • Garðar Ingvarsson
  • Timon Willi
  • Ravi Hammond

Benchmarks are crucial in the development of machine learning algorithms, significantly influencing reinforcement learning (RL) research through the available environments. Traditionally, RL environments run on the CPU, which limits their scalability with the computational resources typically available in academia. However, recent advancements in JAX have enabled the wider use of hardware acceleration, enabling massively parallel RL training pipelines and environments. While this has been successfully applied to single-agent RL, it has not yet been widely adopted for multi-agent scenarios. In this paper, we present JaxMARL, the first open-source, easy-to-use code base that combines GPU-enabled efficiency with support for a large number of commonly used MARL environments and popular baseline algorithms. Our experiments show that, in terms of wall clock time, our JAX-based training pipeline is up to 12, 500 times faster than existing approaches. This enables efficient and thorough evaluations, potentially alleviating the evaluation crisis in the field. We also introduce and benchmark SMAX, a vectorised, simplified version of the popular StarCraft Multi-Agent Challenge, which removes the need to run the StarCraft II game engine. This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL. The code is available at https: //github. com/flairox/jaxmarl.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery

  • Alex Rutherford
  • Michael Beukman
  • Timon Willi
  • Bruno Lacerda
  • Nick Hawes
  • Jakob Foerster

What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised Environment Design (UED) methods have gained recent attention as their adaptive curricula promise to enable agents to be robust to in- and out-of-distribution tasks. This work investigates how existing UED methods select training environments, focusing on task prioritisation metrics. Surprisingly, despite methods aiming to maximise regret in theory, the practical approximations do not correlate with regret but with success rate. As a result, a significant portion of an agent's experience comes from environments it has already mastered, offering little to no contribution toward enhancing its abilities. Put differently, current methods fail to predict intuitive measures of learnability. Specifically, they are unable to consistently identify those scenarios that the agent can sometimes solve, but not always. Based on our analysis, we develop a method that directly trains on scenarios with high learnability. This simple and intuitive approach outperforms existing UED methods in several binary-outcome environments, including the standard domain of Minigrid and a novel setting closely inspired by a real-world robotics problem. We further introduce a new adversarial evaluation procedure for directly measuring robustness, closely mirroring the conditional value at risk (CVaR). We open-source all our code and present visualisations of final policies here: https: //github. com/amacrutherford/sampling-for-learnability.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

  • Mikayel Samvelyan
  • Sharath C. Raparthy
  • Andrei Lupu
  • Eric Hambro
  • Aram H. Markosyan
  • Manish Bhatt
  • Yuning Mao
  • Minqi Jiang

As large language models (LLMs) become increasingly prevalent across many real-world applications, understanding and enhancing their robustness to adversarial attacks is of paramount importance. Existing methods for identifying adversarial prompts tend to focus on specific domains, lack diversity, or require extensive human annotations. To address these limitations, we present Rainbow Teaming, a novel black-box approach for producing a diverse collection of adversarial prompts. Rainbow Teaming casts adversarial prompt generation as a quality-diversity problem and uses open-ended search to generate prompts that are both effective and diverse. Focusing on the safety domain, we use Rainbow Teaming to target various state-of-the-art LLMs, including the Llama 2 and Llama 3 models. Our approach reveals hundreds of effective adversarial prompts, with an attack success rate exceeding 90% across all tested models. Furthermore, we demonstrate that prompts generated by Rainbow Teaming are highly transferable and that fine-tuning models with synthetic data generated by our method significantly enhances their safety without sacrificing general performance or helpfulness. We additionally explore the versatility of Rainbow Teaming by applying it to question answering and cybersecurity, showcasing its potential to drive robust open-ended self-improvement in a wide range of applications.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Recurrent Reinforcement Learning with Memoroids

  • Steven Morad
  • Chris Lu
  • Ryan Kortvelesy
  • Stephan Liwicki
  • Jakob Foerster
  • Amanda Prorok

Memory models such as Recurrent Neural Networks (RNNs) and Transformers address Partially Observable Markov Decision Processes (POMDPs) by mapping trajectories to latent Markov states. Neither model scales particularly well to long sequences, especially compared to an emerging class of memory models called Linear Recurrent Models. We discover that the recurrent update of these models resembles a monoid, leading us to reformulate existing models using a novel monoid-based framework that we call memoroids. We revisit the traditional approach to batching in recurrent reinforcement learning, highlighting theoretical and empirical deficiencies. We leverage memoroids to propose a batching method that improves sample efficiency, increases the return, and simplifies the implementation of recurrent loss functions in reinforcement learning.

PDF Details DOI

AAMAS Conference 2024 Conference Paper

Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection

  • Linas Nasvytis
  • Kai Sandbrink
  • Jakob Foerster
  • Tim Franzmeyer
  • Christian Schroeder de Witt

While reinforcement learning (RL) algorithms have been successfully applied across numerous sequential decision-making problems, their generalization to unforeseen testing environments remains a significant concern. In this paper, we study the problem of out-of-distribution (OOD) detection in RL, which focuses on identifying situations at test time that RL agents have not encountered in their training environments. We first propose a clarification of terminology for OOD detection in RL, which aligns it with the literature from other machine learning domains. We then present new benchmark scenarios for OOD detection, which introduce anomalies with temporal autocorrelation into different components of the agent-environment loop. We argue that such scenarios have been understudied in the current literature, despite their relevance to real-world situations. Confirming our theoretical predictions, our experimental results suggest that state-of-the-art OOD detectors are not able to identify such anomalies. To address this problem, we propose a novel method for OOD detection, which we call DEX- TER (Detection via Extraction of Time Series Representations). By treating environment observations as time series data, DEXTER extracts salient time series features, and then leverages an ensemble of isolation forest algorithms to detect anomalies. We find that DEX- TER can reliably identify anomalies across benchmark scenarios, exhibiting superior performance compared to both state-of-theart OOD detectors and high-dimensional changepoint detectors adopted from statistics.

PDF

AAMAS Conference 2024 Conference Paper

Scaling Opponent Shaping to High Dimensional Games

  • Akbir Khan
  • Timon Willi
  • Newton Kwan
  • Andrea Tacchetti
  • Chris Lu
  • Edward Grefenstette
  • Tim Rocktäschel
  • Jakob Foerster

In multi-agent settings with mixed incentives, methods developed for zero-sum games have been shown to lead to detrimental outcomes. To address this issue, opponent shaping (OS) methods explicitly learn to influence the learning dynamics of co-players and empirically lead to improved individual and collective outcomes. However, OS methods have only been evaluated in low-dimensional environments due to the challenges associated with estimating higher-order derivatives or scaling model-free meta-learning. Alternative methods that scale to more complex settings either converge to undesirable solutions or rely on unrealistic assumptions about the environment or co-players. In this paper, we successfully scale an OS-based approach to general-sum games with temporallyextended actions and long-time horizons for the first time. After analysing the representations of the meta-state and history used by previous algorithms, we propose a simplified version called Shaper. We show empirically that Shaper leads to improved individual and collective outcomes in a range of challenging settings from literature. We further formalize a technique previously implicit in the literature, and analyse its contribution to opponent shaping. We show empirically that this technique is helpful for the functioning of prior methods in certain environments. Lastly, we show that previous environments, such as the CoinGame, are inadequate for analysing temporally-extended general-sum interactions1.

PDF

NeurIPS Conference 2023 Conference Paper

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design

  • Matthew T Jackson
  • Minqi Jiang
  • Jack Parker-Holder
  • Risto Vuorio
  • Chris Lu
  • Greg Farquhar
  • Shimon Whiteson
  • Jakob Foerster

The past decade has seen vast progress in deep reinforcement learning (RL) on the back of algorithms manually designed by human researchers. Recently, it has been shown that it is possible to meta-learn update rules, with the hope of discovering algorithms that can perform well on a wide range of RL tasks. Despite impressive initial results from algorithms such as Learned Policy Gradient (LPG), there remains a generalization gap when these algorithms are applied to unseen environments. In this work, we examine how characteristics of the meta-training distribution impact the generalization performance of these algorithms. Motivated by this analysis and building on ideas from Unsupervised Environment Design (UED), we propose a novel approach for automatically generating curricula to maximize the regret of a meta-learned optimizer, in addition to a novel approximation of regret, which we name algorithmic regret (AR). The result is our method, General RL Optimizers Obtained Via Environment Design (GROOVE). In a series of experiments, we show that GROOVE achieves superior generalization to LPG, and evaluate AR against baseline metrics from UED, identifying it as a critical component of environment design in this setting. We believe this approach is a step towards the discovery of truly general RL algorithms, capable of solving a wide range of real-world environments.

PDF Details

NeurIPS Conference 2023 Conference Paper

Similarity-based cooperative equilibrium

  • Caspar Oesterheld
  • Johannes Treutlein
  • Roger B. Grosse
  • Vincent Conitzer
  • Jakob Foerster

As machine learning agents act more autonomously in the world, they will increasingly interact with each other. Unfortunately, in many social dilemmas like the one-shot Prisoner’s Dilemma, standard game theory predicts that ML agents will fail to cooperate with each other. Prior work has shown that one way to enable cooperative outcomes in the one-shot Prisoner’s Dilemma is to make the agents mutually transparent to each other, i. e. , to allow them to access one another’s source code (Rubinstein, 1998; Tennenholtz, 2004) – or weights in the case of ML agents. However, full transparency is often unrealistic, whereas partial transparency is commonplace. Moreover, it is challenging for agents to learn their way to cooperation in the full transparency setting. In this paper, we introduce a more realistic setting in which agents only observe a single number indicating how similar they are to each other. We prove that this allows for the same set of cooperative outcomes as the full transparency setting. We also demonstrate experimentally that cooperation can be learned using simple ML methods.

PDF Details

NeurIPS Conference 2023 Conference Paper

SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning

  • Benjamin Ellis
  • Jonathan Cook
  • Skander Moalla
  • Mikayel Samvelyan
  • Mingfei Sun
  • Anuj Mahajan
  • Jakob Foerster
  • Shimon Whiteson

The availability of challenging benchmarks has played a key role in the recent progress of machine learning. In cooperative multi-agent reinforcement learning, the StarCraft Multi-Agent Challenge (SMAC) has become a popular testbed for centralised training with decentralised execution. However, after years of sustained improvement on SMAC, algorithms now achieve near-perfect performance. In this work, we conduct new analysis demonstrating that SMAC lacks the stochasticity and partial observability to require complex closed-loop policies. In particular, we show that an open-loop policy conditioned only on the timestep can achieve non-trivial win rates for many SMAC scenarios. To address this limitation, we introduce SMACv2, a new version of the benchmark where scenarios are procedurally generated and require agents to generalise to previously unseen settings (from the same distribution) during evaluation. We also introduce the extended partial observability challenge (EPO), which augments SMACv2 to ensure meaningful partial observability. We show that these changes ensure the benchmarkrequires the use of closed-loop policies. We evaluate state-of-the-art algorithms on SMACv2 and show that it presents significant challenges not present in the original benchmark. Our analysis illustrates that SMACv2 addresses the discovered deficiencies of SMAC and can help benchmark the next generation of MARL methods. Videos of training are available on our website.

PDF Details

NeurIPS Conference 2023 Conference Paper

Structured State Space Models for In-Context Reinforcement Learning

  • Chris Lu
  • Yannick Schroecker
  • Albert Gu
  • Emilio Parisotto
  • Jakob Foerster
  • Satinder Singh
  • Feryal Behbahani

Structured state space sequence (S4) models have recently achieved state-of-the-art performance on long-range sequence modeling tasks. These models also have fast inference speeds and parallelisable training, making them potentially useful in many reinforcement learning settings. We propose a modification to a variant of S4 that enables us to initialise and reset the hidden state in parallel, allowing us to tackle reinforcement learning tasks. We show that our modified architecture runs asymptotically faster than Transformers in sequence length and performs better than RNN's on a simple memory-based task. We evaluate our modified architecture on a set of partially-observable environments and find that, in practice, our model outperforms RNN's while also running over five times faster. Then, by leveraging the model’s ability to handle long-range sequences, we achieve strong performance on a challenging meta-learning task in which the agent is given a randomly-sampled continuous control environment, combined with a randomly-sampled linear projection of the environment's observations and actions. Furthermore, we show the resulting model can adapt to out-of-distribution held-out tasks. Overall, the results presented in this paper show that structured state space models are fast and performant for in-context reinforcement learning tasks. We provide code at https: //github. com/luchris429/s5rl.

PDF Details

AAMAS Conference 2022 Conference Paper

Centralized Model and Exploration Policy for Multi-Agent RL

  • Qizhen Zhang
  • Chris Lu
  • Animesh Garg
  • Jakob Foerster

Reinforcement learning (RL) in partially observable, fully cooperative multi-agent settings (Dec-POMDPs) can in principle be used to address many real-world challenges such as controlling a swarm of rescue robots or a team of quadcopters. However, Dec-POMDPs are significantly harder to solve than single-agent problems, with the former being NEXP-complete and the latter, MDPs, being just P-complete. Hence, current RL algorithms for Dec-POMDPs suffer from poor sample complexity, which greatly reduces their applicability to practical problems where environment interaction is costly. Our key insight is that using just a polynomial number of samples, one can learn a centralized model that generalizes across different policies. We can then optimize the policy within the learned model instead of the true system, without requiring additional environment interactions. We also learn a centralized exploration policy within our model that learns to collect additional data in state-action regions with high model uncertainty. We empirically evaluate the proposed model-based algorithm, MARCO∗, in three cooperative communication tasks, where it improves sample efficiency by up to 20x. Finally, to investigate the theoretical sample complexity, we adapt an existing model-based method for tabular MDPs to Dec-POMDPs, and prove that it achieves polynomial sample complexity.

PDF

NeurIPS Conference 2022 Conference Paper

Discovered Policy Optimisation

  • Chris Lu
  • Jakub Kuba
  • Alistair Letcher
  • Luke Metz
  • Christian Schroeder de Witt
  • Jakob Foerster

Tremendous progress has been made in reinforcement learning (RL) over the past decade. Most of these advancements came through the continual development of new algorithms, which were designed using a combination of mathematical derivations, intuitions, and experimentation. Such an approach of creating algorithms manually is limited by human understanding and ingenuity. In contrast, meta-learning provides a toolkit for automatic machine learning method optimisation, potentially addressing this flaw. However, black-box approaches which attempt to discover RL algorithms with minimal prior structure have thus far not outperformed existing hand-crafted algorithms. Mirror Learning, which includes RL algorithms, such as PPO, offers a potential middle-ground starting point: while every method in this framework comes with theoretical guarantees, components that differentiate them are subject to design. In this paper we explore the Mirror Learning space by meta-learning a “drift” function. We refer to the immediate result as Learnt Policy Optimisation (LPO). By analysing LPO we gain original insights into policy optimisation which we use to formulate a novel, closed-form RL algorithm, Discovered Policy Optimisation (DPO). Our experiments in Brax environments confirm state-of-the-art performance of LPO and DPO, as well as their transfer to unseen settings.

PDF Details

NeurIPS Conference 2022 Conference Paper

Equivariant Networks for Zero-Shot Coordination

  • Darius Muglich
  • Christian Schroeder de Witt
  • Elise van der Pol
  • Shimon Whiteson
  • Jakob Foerster

Successful coordination in Dec-POMDPs requires agents to adopt robust strategies and interpretable styles of play for their partner. A common failure mode is symmetry breaking, when agents arbitrarily converge on one out of many equivalent but mutually incompatible policies. Commonly these examples include partial observability, e. g. waving your right hand vs. left hand to convey a covert message. In this paper, we present a novel equivariant network architecture for use in Dec-POMDPs that prevents the agent from learning policies which break symmetries, doing so more effectively than prior methods. Our method also acts as a "coordination-improvement operator" for generic, pre-trained policies, and thus may be applied at test-time in conjunction with any self-play algorithm. We provide theoretical guarantees of our work and test on the AI benchmark task of Hanabi, where we demonstrate our methods outperforming other symmetry-aware baselines in zero-shot coordination, as well as able to improve the coordination ability of a variety of pre-trained policies. In particular, we show our method can be used to improve on the state of the art for zero-shot coordination on the Hanabi benchmark.

PDF Details

NeurIPS Conference 2022 Conference Paper

Grounding Aleatoric Uncertainty for Unsupervised Environment Design

  • Minqi Jiang
  • Michael Dennis
  • Jack Parker-Holder
  • Andrei Lupu
  • Heinrich Küttler
  • Edward Grefenstette
  • Tim Rocktäschel
  • Jakob Foerster

Adaptive curricula in reinforcement learning (RL) have proven effective for producing policies robust to discrepancies between the train and test environment. Recently, the Unsupervised Environment Design (UED) framework generalized RL curricula to generating sequences of entire environments, leading to new methods with robust minimax regret properties. Problematically, in partially-observable or stochastic settings, optimal policies may depend on the ground-truth distribution over aleatoric parameters of the environment in the intended deployment setting, while curriculum learning necessarily shifts the training distribution. We formalize this phenomenon as curriculum-induced covariate shift (CICS), and describe how its occurrence in aleatoric parameters can lead to suboptimal policies. Directly sampling these parameters from the ground-truth distribution avoids the issue, but thwarts curriculum learning. We propose SAMPLR, a minimax regret UED method that optimizes the ground-truth utility function, even when the underlying training data is biased due to CICS. We prove, and validate on challenging domains, that our approach preserves optimality under the ground-truth distribution, while promoting robustness across the full range of environment settings.

PDF Details

NeurIPS Conference 2022 Conference Paper

Influencing Long-Term Behavior in Multiagent Reinforcement Learning

  • Dong-Ki Kim
  • Matthew Riemer
  • Miao Liu
  • Jakob Foerster
  • Michael Everett
  • Chuangchuang Sun
  • Gerald Tesauro
  • Jonathan P. How

The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment's transition and reward dynamics. An effective approach that has recently emerged for addressing this non-stationarity is for each agent to anticipate the learning of other agents and influence the evolution of future policies towards desirable behavior for its own benefit. Unfortunately, previous approaches for achieving this suffer from myopic evaluation, considering only a finite number of policy updates. As such, these methods can only influence transient future policies rather than achieving the promise of scalable equilibrium selection approaches that influence the behavior at convergence. In this paper, we propose a principled framework for considering the limiting policies of other agents as time approaches infinity. Specifically, we develop a new optimization objective that maximizes each agent's average reward by directly accounting for the impact of its behavior on the limiting set of policies that other agents will converge to. Our paper characterizes desirable solution concepts within this problem setting and provides practical approaches for optimizing over possible outcomes. As a result of our farsighted objective, we demonstrate better long-term performance than state-of-the-art baselines across a suite of diverse multiagent benchmark domains.

PDF Details

AAMAS Conference 2022 Conference Paper

Lyapunov Exponents for Diversity in Differentiable Games

  • Jonathan Lorraine
  • Paul Vicol
  • Jack Parker-Holder
  • Tal Kachman
  • Luke Metz
  • Jakob Foerster

Ridge Rider (RR) is an algorithm for finding diverse solutions to optimization problems by following eigenvectors of the Hessian (“ridges”). RR is designed for conservative gradient systems (i. e. , settings involving a single loss function), where it branches at saddles — easy-to-find bifurcation points. We generalize this idea to nonconservative, multi-agent gradient systems by proposing a method – denoted Generalized Ridge Rider (GRR) – for finding arbitrary bifurcation points. We give theoretical motivation for our method by leveraging machinery from the field of dynamical systems. We construct novel toy problems where we can visualize new phenomena while giving insight into high-dimensional problems of interest. Finally, we empirically evaluate our method by finding diverse solutions in the iterated prisoners’ dilemma and relevant machine learning problems including generative adversarial networks.

PDF

NeurIPS Conference 2022 Conference Paper

Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real world

  • Eugene Vinitsky
  • Nathan Lichtlé
  • Xiaomeng Yang
  • Brandon Amos
  • Jakob Foerster

We introduce \textit{Nocturne}, a new 2D driving simulator for investigating multi-agent coordination under partial observability. The focus of Nocturne is to enable research into inference and theory of mind in real-world multi-agent settings without the computational overhead of computer vision and feature extraction from images. Agents in this simulator only observe an obstructed view of the scene, mimicking human visual sensing constraints. Unlike existing benchmarks that are bottlenecked by rendering human-like observations directly using a camera input, Nocturne uses efficient intersection methods to compute a vectorized set of visible features in a C++ back-end, allowing the simulator to run at $2000+$ steps-per-second. Using open-source trajectory and map data, we construct a simulator to load and replay arbitrary trajectories and scenes from real-world driving data. Using this environment, we benchmark reinforcement-learning and imitation-learning agents and demonstrate that the agents are quite far from human-level coordination ability and deviate significantly from the expert trajectories.

PDF Details

NeurIPS Conference 2022 Conference Paper

Off-Team Learning

  • Brandon Cui
  • Hengyuan Hu
  • Andrei Lupu
  • Samuel Sokota
  • Jakob Foerster

Zero-shot coordination (ZSC) evaluates an algorithm by the performance of a team of agents that were trained independently under that algorithm. Off-belief learning (OBL) is a recent method that achieves state-of-the-art results in ZSC in the game Hanabi. However, the implementation of OBL relies on a belief model that experiences covariate shift. Moreover, during ad-hoc coordination, OBL or any other neural policy may experience test-time covariate shift. We present two methods addressing these issues. The first method, off-team belief learning (OTBL), attempts to improve the accuracy of the belief model of a target policy πT on a broader range of inputs by weighting trajectories approximately according to the distribution induced by a different policy πb. The second, off-team off-belief learning (OT-OBL), attempts to compute an OBL equilibrium, where fixed point error is weighted according to the distribution induced by cross-play between the training policy π and a different fixed policy πb instead of self-play of π. We investigate these methods in variants of Hanabi.

PDF Details

NeurIPS Conference 2022 Conference Paper

Proximal Learning With Opponent-Learning Awareness

  • Stephen Zhao
  • Chris Lu
  • Roger B. Grosse
  • Jakob Foerster

Learning With Opponent-Learning Awareness (LOLA) (Foerster et al. [2018a]) is a multi-agent reinforcement learning algorithm that typically learns reciprocity-based cooperation in partially competitive environments. However, LOLA often fails to learn such behaviour on more complex policy spaces parameterized by neural networks, partly because the update rule is sensitive to the policy parameterization. This problem is especially pronounced in the opponent modeling setting, where the opponent's policy is unknown and must be inferred from observations; in such settings, LOLA is ill-specified because behaviorally equivalent opponent policies can result in non-equivalent updates. To address this shortcoming, we reinterpret LOLA as approximating a proximal operator, and then derive a new algorithm, proximal LOLA (POLA), which uses the proximal formulation directly. Unlike LOLA, the POLA updates are parameterization invariant, in the sense that when the proximal objective has a unique optimum, behaviorally equivalent policies result in behaviorally equivalent updates. We then present practical approximations to the ideal POLA update, which we evaluate in several partially competitive environments with function approximation and opponent modeling. This empirically demonstrates that POLA achieves reciprocity-based cooperation more reliably than LOLA.

PDF Details

NeurIPS Conference 2022 Conference Paper

Self-Explaining Deviations for Coordination

  • Hengyuan Hu
  • Samuel Sokota
  • David Wu
  • Anton Bakhtin
  • Andrei Lupu
  • Brandon Cui
  • Jakob Foerster

Fully cooperative, partially observable multi-agent problems are ubiquitous in the real world. In this paper, we focus on a specific subclass of coordination problems in which humans are able to discover self-explaining deviations (SEDs). SEDs are actions that deviate from the common understanding of what reasonable behavior would be in normal circumstances. They are taken with the intention of causing another agent or other agents to realize, using theory of mind, that the circumstance must be abnormal. We motivate this idea with a real world example and formalize its definition. Next, we introduce an algorithm for improvement maximizing SEDs (IMPROVISED). Lastly, we evaluate IMPROVISED both in an illustrative toy setting and the popular benchmark setting Hanabi, where we show that it can produce so called finesse plays.

PDF Details

NeurIPS Conference 2021 Conference Paper

K-level Reasoning for Zero-Shot Coordination in Hanabi

  • Brandon Cui
  • Hengyuan Hu
  • Luis Pineda
  • Jakob Foerster

The standard problem setting in cooperative multi-agent settings is \emph{self-play} (SP), where the goal is to train a \emph{team} of agents that works well together. However, optimal SP policies commonly contain arbitrary conventions (``handshakes'') and are not compatible with other, independently trained agents or humans. This latter desiderata was recently formalized by \cite{Hu2020-OtherPlay} as the \emph{zero-shot coordination} (ZSC) setting and partially addressed with their \emph{Other-Play} (OP) algorithm, which showed improved ZSC and human-AI performance in the card game Hanabi. OP assumes access to the symmetries of the environment and prevents agents from breaking these in a mutually \emph{incompatible} way during training. However, as the authors point out, discovering symmetries for a given environment is a computationally hard problem. Instead, we show that through a simple adaption of k-level reasoning (KLR) \cite{Costa-Gomes2006-K-level}, synchronously training all levels, we can obtain competitive ZSC and ad-hoc teamplay performance in Hanabi, including when paired with a human-like proxy bot. We also introduce a new method, synchronous-k-level reasoning with a best response (SyKLRBR), which further improves performance on our synchronous KLR by co-training a best response.

PDF Details

NeurIPS Conference 2021 Conference Paper

Neural Pseudo-Label Optimism for the Bank Loan Problem

  • Aldo Pacchiano
  • Shaun Singh
  • Edward Chou
  • Alex Berg
  • Jakob Foerster

We study a class of classification problems best exemplified by the \emph{bank loan} problem, where a lender decides whether or not to issue a loan. The lender only observes whether a customer will repay a loan if the loan is issued to begin with, and thus modeled decisions affect what data is available to the lender for future decisions. As a result, it is possible for the lender's algorithm to ``get stuck'' with a self-fulfilling model. This model never corrects its false negatives, since it never sees the true label for rejected data, thus accumulating infinite regret. In the case of linear models, this issue can be addressed by adding optimism directly into the model predictions. However, there are few methods that extend to the function approximation case using Deep Neural Networks. We present Pseudo-Label Optimism (PLOT), a conceptually and computationally simple method for this setting applicable to DNNs. \PLOT{} adds an optimistic label to the subset of decision points the current model is deciding on, trains the model on all data so far (including these points along with their optimistic labels), and finally uses the resulting \emph{optimistic} model for decision making. \PLOT{} achieves competitive performance on a set of three challenging benchmark problems, requiring minimal hyperparameter tuning. We also show that \PLOT{} satisfies a logarithmic regret guarantee, under a Lipschitz and logistic mean label model, and under a separability condition on the data.

PDF Details

NeurIPS Conference 2021 Conference Paper

Replay-Guided Adversarial Environment Design

  • Minqi Jiang
  • Michael Dennis
  • Jack Parker-Holder
  • Jakob Foerster
  • Edward Grefenstette
  • Tim Rocktäschel

Deep reinforcement learning (RL) agents may successfully generalize to new settings if trained on an appropriately diverse set of environment and task configurations. Unsupervised Environment Design (UED) is a promising self-supervised RL paradigm, wherein the free parameters of an underspecified environment are automatically adapted during training to the agent's capabilities, leading to the emergence of diverse training environments. Here, we cast Prioritized Level Replay (PLR), an empirically successful but theoretically unmotivated method that selectively samples randomly-generated training levels, as UED. We argue that by curating completely random levels, PLR, too, can generate novel and complex levels for effective training. This insight reveals a natural class of UED methods we call Dual Curriculum Design (DCD). Crucially, DCD includes both PLR and a popular UED algorithm, PAIRED, as special cases and inherits similar theoretical guarantees. This connection allows us to develop novel theory for PLR, providing a version with a robustness guarantee at Nash equilibria. Furthermore, our theory suggests a highly counterintuitive improvement to PLR: by stopping the agent from updating its policy on uncurated levels (training on less data), we can improve the convergence to Nash equilibria. Indeed, our experiments confirm that our new method, PLR$^{\perp}$, obtains better results on a suite of out-of-distribution, zero-shot transfer tasks, in addition to demonstrating that PLR$^{\perp}$ improves the performance of PAIRED, from which it inherited its theoretical framework.

PDF Details

AAMAS Conference 2021 Conference Paper

Trajectory Diversity for Zero-Shot Coordination

  • Andrei Lupu
  • Hengyuan Hu
  • Jakob Foerster

We study the problem of zero-shot coordination (ZSC), where agents must independently produce strategies for a collaborative game that are compatible with novel partners not seen during training. In particular, our first contribution is to consider the need for diversity in generating such agents. Because self-play agents control their own trajectory distribution during training, their policy only performs well on this exact distribution. As a result, they achieve low scores in ZSC, since playing with another agent is likely to put them in situations they have not encountered during training. To address this issue, we train a common best response (BR) to a population of agents, which we regulate to be as diverse as possible. For that purpose, we introduce Trajectory Diversity (TrajeDi) - a differentiable objective for generating diverse reinforcement learning (RL) policies. We present TrajeDi as a generalization of the Jensen-Shannon divergence (JSD) between policies and motivate it experimentally in a simple matrix game, where it allows to find the unique ZSC-optimal solution.

PDF

AAAI Conference 2020 Conference Paper

Exploratory Combinatorial Optimization with Reinforcement Learning

  • Thomas Barrett
  • William Clements
  • Jakob Foerster
  • Alex Lvovsky

Many real-world problems can be reduced to combinatorial optimization on a graph, where the subset or ordering of vertices that maximize some objective function must be found. With such tasks often NP-hard and analytically intractable, reinforcement learning (RL) has shown promise as a framework with which efficient heuristic methods to tackle these problems can be learned. Previous works construct the solution subset incrementally, adding one element at a time, however, the irreversible nature of this approach prevents the agent from revising its earlier decisions, which may be necessary given the complexity of the optimization task. We instead propose that the agent should seek to continuously improve the solution by learning to explore at test time. Our approach of exploratory combinatorial optimization (ECO- DQN) is, in principle, applicable to any combinatorial problem that can be defined on a graph. Experimentally, we show our method to produce state-of-the-art RL performance on the Maximum Cut problem. Moreover, because ECO-DQN can start from any arbitrary configuration, it can be combined with other search methods to further improve performance, which we demonstrate using a simple random search.

PDF Details

AAAI Conference 2020 Conference Paper

Improving Policies via Search in Cooperative Partially Observable Games

  • Adam Lerer
  • Hengyuan Hu
  • Jakob Foerster
  • Noam Brown

Recent superhuman results in games have largely been achieved in a variety of zero-sum settings, such as Go and Poker, in which agents need to compete against others. However, just like humans, real-world AI systems have to coordinate and communicate with other agents in cooperative partially observable environments as well. These settings commonly require participants to both interpret the actions of others and to act in a way that is informative when being interpreted. Those abilities are typically summarized as theory of mind and are seen as crucial for social interactions. In this paper we propose two different search techniques that can be applied to improve an arbitrary agreed-upon policy in a cooperative partially observable game. The first one, single-agent search, effectively converts the problem into a single agent setting by making all but one of the agents play according to the agreed-upon policy. In contrast, in multi-agent search all agents carry out the same common-knowledge search procedure whenever doing so is computationally feasible, and fall back to playing according to the agreed-upon policy otherwise. We prove that these search procedures are theoretically guaranteed to at least maintain the original performance of the agreed-upon policy (up to a bounded approximation error). In the benchmark challenge problem of Hanabi, our search technique greatly improves the performance of every agent we tested and when applied to a policy trained using RL achieves a new state-of-the-art score of 24. 61 / 25 in the game, compared to a previous-best of 24. 08 / 25.

PDF Details

JMLR Journal 2020 Journal Article

Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning

  • Tabish Rashid
  • Mikayel Samvelyan
  • Christian Schroeder de Witt
  • Gregory Farquhar
  • Jakob Foerster
  • Shimon Whiteson

In many real-world settings, a team of agents must coordinate its behaviour while acting in a decentralised fashion. At the same time, it is often possible to train the agents in a centralised fashion where global state information is available and communication constraints are lifted. Learning joint action-values conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised policies in a centralised end-to-end fashion. QMIX employs a mixing network that estimates joint action-values as a monotonic combination of per-agent values. We structurally enforce that the joint-action value is monotonic in the per-agent values, through the use of non-negative weights in the mixing network, which guarantees consistency between the centralised and decentralised policies. To evaluate the performance of QMIX, we propose the StarCraft Multi-Agent Challenge (SMAC) as a new benchmark for deep multi-agent reinforcement learning. We evaluate QMIX on a challenging set of SMAC scenarios and show that it significantly outperforms existing multi-agent reinforcement learning methods. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2020. ( edit, beta )

PDF Details

NeurIPS Conference 2020 Conference Paper

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian

  • Jack Parker-Holder
  • Luke Metz
  • Cinjon Resnick
  • Hengyuan Hu
  • Adam Lerer
  • Alistair Letcher
  • Alexander Peysakhovich
  • Aldo Pacchiano

Over the last decade, a single algorithm has changed many facets of our lives - Stochastic Gradient Descent (SGD). In the era of ever decreasing loss functions, SGD and its various offspring have become the go-to optimization tool in machine learning and are a key component of the success of deep neural networks (DNNs). While SGD is guaranteed to converge to a local optimum (under loose assumptions), in some cases it may matter which local optimum is found, and this is often context-dependent. Examples frequently arise in machine learning, from shape-versus-texture-features to ensemble methods and zero-shot coordination. In these settings, there are desired solutions which SGD on standard' loss functions will not find, since it instead converges to the easy' solutions. In this paper, we present a different approach. Rather than following the gradient, which corresponds to a locally greedy direction, we instead follow the eigenvectors of the Hessian. By iteratively following and branching amongst the ridges, we effectively span the loss surface to find qualitatively different solutions. We show both theoretically and experimentally that our method, called Ridge Rider (RR), offers a promising direction for a variety of challenging problems.

PDF Details

IJCAI Conference 2019 Conference Paper

A Survey of Reinforcement Learning Informed by Natural Language

  • Jelena Luketina
  • Nantas Nardelli
  • Gregory Farquhar
  • Jakob Foerster
  • Jacob Andreas
  • Edward Grefenstette
  • Shimon Whiteson
  • Tim Rocktäschel

To be successful in real-world tasks, Reinforcement Learning (RL) needs to exploit the compositional, relational, and hierarchical structure of the world, and learn to transfer it to the task at hand. Recent advances in representation learning for language make it possible to build models that acquire world knowledge from text corpora and integrate this knowledge into downstream decision making problems. We thus argue that the time is right to investigate a tight integration of natural language understanding into RL in particular. We survey the state of the field, including work on instruction following, text games, and learning from textual domain knowledge. Finally, we call for the development of new environments as well as further investigation into the potential uses of recent Natural Language Processing (NLP) techniques for such tasks.

PDF Details

JMLR Journal 2019 Journal Article

Differentiable Game Mechanics

  • Alistair Letcher
  • David Balduzzi
  • Sébastien Racanière
  • James Martens
  • Jakob Foerster
  • Karl Tuyls
  • Thore Graepel

Deep learning is built on the foundational guarantee that gradient descent on an objective function converges to local minima. Unfortunately, this guarantee fails in settings, such as generative adversarial nets, that exhibit multiple interacting losses. The behavior of gradient-based methods in games is not well understood -- and is becoming increasingly important as adversarial and multi-objective architectures proliferate. In this paper, we develop new tools to understand and control the dynamics in $n$-player differentiable games. The key result is to decompose the game Jacobian into two components. The first, symmetric component, is related to potential games, which reduce to gradient descent on an implicit function. The second, antisymmetric component, relates to Hamiltonian games, a new class of games that obey a conservation law akin to conservation laws in classical mechanical systems. The decomposition motivates Symplectic Gradient Adjustment (SGA), a new algorithm for finding stable fixed points in differentiable games. Basic experiments show SGA is competitive with recently proposed algorithms for finding stable fixed points in GANs -- while at the same time being applicable to, and having guarantees in, much more general cases. [abs] [ pdf ][ bib ] &copy JMLR 2019. ( edit, beta )

PDF Details

NeurIPS Conference 2019 Conference Paper

Loaded DiCE: Trading off Bias and Variance in Any-Order Score Function Gradient Estimators for Reinforcement Learning

  • Gregory Farquhar
  • Shimon Whiteson
  • Jakob Foerster

Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance unbiased estimators of derivatives at any order. Our objective is compatible with arbitrary advantage estimators, which allows the control of the bias and variance of any-order derivatives when using function approximation. Furthermore, we propose a method to trade off bias and variance of higher order derivatives by discounting the impact of more distant causal dependencies. We demonstrate the correctness and utility of our estimator in analytically tractable MDPs and in meta-reinforcement-learning for continuous control.

PDF Details

NeurIPS Conference 2019 Conference Paper

Multi-Agent Common Knowledge Reinforcement Learning

  • Christian Schroeder de Witt
  • Jakob Foerster
  • Gregory Farquhar
  • Philip Torr
  • Wendelin Boehmer
  • Shimon Whiteson

Cooperative multi-agent reinforcement learning often requires decentralised policies, which severely limit the agents' ability to coordinate their behaviour. In this paper, we show that common knowledge between agents allows for complex decentralised coordination. Common knowledge arises naturally in a large number of decentralised cooperative multi-agent tasks, for example, when agents can reconstruct parts of each others' observations. Since agents can independently agree on their common knowledge, they can execute complex coordinated policies that condition on this knowledge in a fully decentralised fashion. We propose multi-agent common knowledge reinforcement learning (MACKRL), a novel stochastic actor-critic algorithm that learns a hierarchical policy tree. Higher levels in the hierarchy coordinate groups of agents by conditioning on their common knowledge, or delegate to lower levels with smaller subgroups but potentially richer common knowledge. The entire policy tree can be executed in a fully decentralised fashion. As the lowest policy tree level consists of independent policies for each agent, MACKRL reduces to independently learnt decentralised policies as a special case. We demonstrate that our method can exploit common knowledge for superior performance on complex decentralised coordination tasks, including a stochastic matrix game and challenging problems in StarCraft II unit micromanagement.

PDF Details

AAMAS Conference 2019 Conference Paper

On the Pitfalls of Measuring Emergent Communication

  • Ryan Lowe
  • Jakob Foerster
  • Y-Lan Boureau
  • Joelle Pineau
  • Yann Dauphin

How do we know if communication is emerging in a multi-agent system? The vast majority of recent papers on emergent communication show that adding a communication channel leads to an increase in reward or task success. This is a useful indicator, but provides only a coarse measure of the agent’s learned communication abilities. As we move towards more complex environments, it becomes imperative to have a set of iner tools that allow qualitative and quantitative insights into the emergence of communication. This may be especially useful to allow humans to monitor agents’ behaviour, whether for fault detection, assessing performance, or even building trust. In this paper, we examine a few intuitive existing metrics for measuring communication, and show that they can be misleading. Speciically, by training deep reinforcement learning agents to play simple matrix games augmented with a communication channel, we ind a scenario where agents appear to communicate (their messages provide information about their subsequent action), and yet the messages do not impact the environment or other agent in any way. We explain this phenomenon using ablation studies and by visualizing the representations of the learned policies. We also survey some commonly used metrics for measuring emergent communication, and provide recommendations as to when these metrics should be used.

PDF

AAMAS Conference 2019 Conference Paper

The StarCraft Multi-Agent Challenge

  • Mikayel Samvelyan
  • Tabish Rashid
  • Christian Schroeder de Witt
  • Gregory Farquhar
  • Nantas Nardelli
  • Tim G. J. Rudner
  • Chia-Man Hung
  • Philip H. S. Torr

In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents must learn to coordinate their behaviour while conditioning only on their private observations. This is an attractive research area since such problems are relevant to a large number of real-world systems and are also more amenable to evaluation than general-sum problems. Standardised environments such as the ALE and MuJoCo have allowed single-agent RL to move beyond toy domains, such as grid worlds. However, there is no comparable benchmark for cooperative multi-agent RL. As a result, most papers in this field use one-off toy problems, making it difficult to measure real progress. In this paper, we propose the StarCraft Multi-Agent Challenge (SMAC) as a benchmark problem to fill this gap. 1 SMAC is based on the popular real-time strategy game StarCraft II and focuses on micromanagement challenges where each unit is controlled by an independent agent that must act based on local observations. We offer a diverse set of challenge maps and recommendations for best practices in benchmarking and evaluations. We also open-source a deep multi-agent RL learning framework including state-of-theart algorithms. 2 We believe that SMAC can provide a standard benchmark environment for years to come. Videos of our best agents for several SMAC scenarios are available at: https: //youtu. be/VZ7zmQ_obZ0.

PDF

AAAI Conference 2018 Conference Paper

Counterfactual Multi-Agent Policy Gradients

  • Jakob Foerster
  • Gregory Farquhar
  • Triantafyllos Afouras
  • Nantas Nardelli
  • Shimon Whiteson

Many real-world problems, such as network packet routing and the coordination of autonomous vehicles, are naturally modelled as cooperative multi-agent systems. There is a great need for new reinforcement learning methods that can ef- ficiently learn decentralised policies for such systems. To this end, we propose a new multi-agent actor-critic method called counterfactual multi-agent (COMA) policy gradients. COMA uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents’ policies. In addition, to address the challenges of multi-agent credit assignment, it uses a counterfactual baseline that marginalises out a single agent’s action, while keeping the other agents’ actions fixed. COMA also uses a critic representation that allows the counterfactual baseline to be computed efficiently in a single forward pass. We evaluate COMA in the testbed of StarCraft unit micromanagement, using a decentralised variant with significant partial observability. COMA significantly improves average performance over other multi-agent actorcritic methods in this setting, and the best performing agents are competitive with state-of-the-art centralised controllers that get access to the full state.

PDF Details

AAMAS Conference 2018 Conference Paper

Learning with Opponent-Learning Awareness

  • Jakob Foerster
  • Richard Y. Chen
  • Maruan Al-Shedivat
  • Shimon Whiteson
  • Pieter Abbeel
  • Igor Mordatch

Multi-agent settings are quickly gathering importance in machine learning. This includes a plethora of recent work on deep multiagent reinforcement learning, but also can be extended to hierarchical reinforcement learning, generative adversarial networks and decentralised optimization. In all these settings the presence of multiple learning agents renders the training problem non-stationary and often leads to unstable training or undesired final results. We present Learning with Opponent-Learning Awareness (LOLA), a method in which each agent shapes the anticipated learning of the other agents in the environment. The LOLA learning rule includes an additional term that accounts for the impact of one agent’s policy on the anticipated parameter update of the other agents. Preliminary results show that the encounter of two LOLA agents leads to the emergence of tit-for-tat and therefore cooperation in the iterated prisoners’ dilemma (IPD), while independent learning does not. In this domain, LOLA also receives higher payouts compared to a naive learner, and is robust against exploitation by higher order gradient-based methods. Applied to infinitely repeated matching pennies, LOLA agents converge to the Nash equilibrium. In a round robin tournament we show that LOLA agents can successfully shape the learning of a range of multi-agent learning algorithms from literature, resulting in the highest average returns on the IPD. We also show that the LOLA update rule can be efficiently calculated using an extension of the likelihood ratio policy gradient estimator, making the method suitable for model-free reinforcement learning. This method thus scales to large parameter and input spaces and nonlinear function approximators. We also apply LOLA to a grid world task with an embedded social dilemma using deep recurrent policies and opponent modelling. Again, by explicitly considering the learning of the other agent, LOLA agents learn to cooperate out of self-interest.

PDF

NeurIPS Conference 2016 Conference Paper

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

  • Jakob Foerster
  • Ioannis Alexandros Assael
  • Nando de Freitas
  • Shimon Whiteson

We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks. By embracing deep neural networks, we are able to demonstrate end-to-end learning of protocols in complex environments inspired by communication riddles and multi-agent computer vision problems with partial observability. We propose two approaches for learning in these domains: Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter-Agent Learning (DIAL). The former uses deep Q-learning, while the latter exploits the fact that, during learning, agents can backpropagate error derivatives through (noisy) communication channels. Hence, this approach uses centralised learning but decentralised execution. Our experiments introduce new environments for studying the learning of communication protocols and present a set of engineering innovations that are essential for success in these domains.

PDF Details