Author name cluster

Louis Kirsch

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.

13 papers

2 author rows

TMLR Journal 2025 Journal Article

Understanding In-Context Learning of Linear Models in Transformers Through an Adversarial Lens

Usman Anwar
Johannes von Oswald
Louis Kirsch
David Krueger
Spencer Frei

In this work, we make two contributions towards understanding of in-context learning of linear models by transformers. First, we investigate the adversarial robustness of in-context learning in transformers to hijacking attacks — a type of adversarial attacks in which the adversary’s goal is to manipulate the prompt to force the transformer to generate a specific output. We show that both linear transformers and transformers with GPT-2 architectures are vulnerable to such hijacking attacks. However, adversarial robustness to such attacks can be significantly improved through adversarial training --- done either at the pretraining or finetuning stage --- and can generalize to stronger attack models. Our second main contribution is a comparative analysis of adversarial vulnerabilities across transformer models and other algorithms for learning linear models. This reveals two novel findings. First, adversarial attacks transfer poorly between larger transformer models trained from different seeds despite achieving similar in-distribution performance. This suggests that transformers of the same architecture trained according to the same recipe may implement different in-context learning algorithms for the same task. Second, we observe that attacks do not transfer well between classical learning algorithms for linear models (single-step gradient descent and ordinary least squares) and transformers. This suggests that there could be qualitative differences between the in-context learning algorithms that transformers implement and these traditional algorithms.

PDF Details

ICLR Conference 2024 Conference Paper

Discovering Temporally-Aware Reinforcement Learning Algorithms

Matthew Thomas Jackson
Chris Lu 0001
Louis Kirsch
Robert Tjarko Lange
Shimon Whiteson
Jakob N. Foerster

Recent advancements in meta-learning have enabled the automatic discovery of novel reinforcement learning algorithms parameterized by surrogate objective functions. To improve upon manually designed algorithms, the parameterization of this learned objective function must be expressive enough to represent novel principles of learning (instead of merely recovering already established ones) while still generalizing to a wide range of settings outside of its meta-training distribution. However, existing methods focus on discovering objective functions that, like many widely used objective functions in reinforcement learning, do not take into account the total number of steps allowed for training, or “training horizon”. In contrast, humans use a plethora of different learning objectives across the course of acquiring a new ability. For instance, students may alter their studying techniques based on the proximity to exam deadlines and their self-assessed capabilities. This paper contends that ignoring the optimization time horizon significantly restricts the expressive potential of discovered learning algorithms. We propose a simple augmentation to two existing objective discovery approaches that allows the discovered algorithm to dynamically update its objective function throughout the agent’s training procedure, resulting in expressive schedules and increased generalization across different training horizons. In the process, we find that commonly used meta-gradient approaches fail to discover such adaptive objective functions while evolution strategies discover highly dynamic learning rules. We demonstrate the effectiveness of our approach on a wide range of tasks and analyze the resulting learned algorithms, which we find effectively balance exploration and exploitation by modifying the structure of their learning rules throughout the agent’s lifetime.

Details

ICML Conference 2024 Conference Paper

GPTSwarm: Language Agents as Optimizable Graphs

Mingchen Zhuge
Wenyi Wang
Louis Kirsch
Francesco Faccio
Dmitrii Khizbullin
Jürgen Schmidhuber

Various human-designed prompt engineering techniques have been proposed to improve problem solvers based on Large Language Models (LLMs), yielding many disparate code bases. We unify these approaches by describing LLM-based agents as computational graphs. The nodes implement functions to process multimodal data or query LLMs, and the edges describe the information flow between operations. Graphs can be recursively combined into larger composite graphs representing hierarchies of inter-agent collaboration (where edges connect operations of different agents). Our novel automatic graph optimizers (1) refine node-level LLM prompts (node optimization) and (2) improve agent orchestration by changing graph connectivity (edge optimization). Experiments demonstrate that our framework can be used to efficiently develop, integrate, and automatically improve various LLM agents. Our code is public.

Details

ICML Conference 2024 Conference Paper

Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning

Aditya A. Ramesh
Kenny Young
Louis Kirsch
Jürgen Schmidhuber

Temporal credit assignment in reinforcement learning is challenging due to delayed and stochastic outcomes. Monte Carlo targets can bridge long delays between action and consequence but lead to high-variance targets due to stochasticity. Temporal difference (TD) learning uses bootstrapping to overcome variance but introduces a bias that can only be corrected through many iterations. TD($\lambda$) provides a mechanism to navigate this bias-variance tradeoff smoothly. Appropriately selecting $\lambda$ can significantly improve performance. Here, we propose Chunked-TD, which uses predicted probabilities of transitions from a model for computing $\lambda$-return targets. Unlike other model-based solutions to credit assignment, Chunked-TD is less vulnerable to model inaccuracies. Our approach is motivated by the principle of history compression and ‘chunks’ trajectories for conventional TD learning. Chunking with learned world models compresses near-deterministic regions of the environment-policy interaction to speed up credit assignment while still bootstrapping when necessary. We propose algorithms that can be implemented online and show that they solve some problems much faster than conventional TD($\lambda$).

Details

AAAI Conference 2023 Conference Paper

Goal-Conditioned Generators of Deep Policies

Francesco Faccio
Vincent Herrmann
Aditya Ramesh
Louis Kirsch
Jürgen Schmidhuber

Goal-conditioned Reinforcement Learning (RL) aims at learning optimal policies, given goals encoded in special command inputs. Here we study goal-conditioned neural nets (NNs) that learn to generate deep NN policies in form of context-specific weight matrices, similar to Fast Weight Programmers and other methods from the 1990s. Using context commands of the form ``generate a policy that achieves a desired expected return,'' our NN generators combine powerful exploration of parameter space with generalization across commands to iteratively find better and better policies. A form of weight-sharing HyperNetworks and policy embeddings scales our method to generate deep NNs. Experiments show how a single learned policy generator can produce policies that achieve any return seen during training. Finally, we evaluate our algorithm on a set of continuous control tasks where it exhibits competitive performance. Our code is public.

PDF Details DOI

ICML Conference 2023 Conference Paper

The Benefits of Model-Based Generalization in Reinforcement Learning

Kenny Young
Aditya A. Ramesh
Louis Kirsch
Jürgen Schmidhuber

Model-Based Reinforcement Learning (RL) is widely believed to have the potential to improve sample efficiency by allowing an agent to synthesize large amounts of imagined experience. Experience Replay (ER) can be considered a simple kind of model, which has proved effective at improving the stability and efficiency of deep RL. In principle, a learned parametric model could improve on ER by generalizing from real experience to augment the dataset with additional plausible experience. However, given that learned value functions can also generalize, it is not immediately obvious why model generalization should be better. Here, we provide theoretical and empirical insight into when, and how, we can expect data generated by a learned model to be useful. First, we provide a simple theorem motivating how learning a model as an intermediate step can narrow down the set of possible value functions more than learning a value function directly from data using the Bellman equation. Second, we provide an illustrative example showing empirically how a similar effect occurs in a more concrete setting with neural network function approximation. Finally, we provide extensive experiments showing the benefit of model-based learning for online RL in environments with combinatorial complexity, but factored structure that allows a learned model to generalize. In these experiments, we take care to control for other factors in order to isolate, insofar as possible, the benefit of using experience generated by a learned model relative to ER alone.

Details

NeurIPS Conference 2022 Conference Paper

Exploring through Random Curiosity with General Value Functions

Aditya Ramesh
Louis Kirsch
Sjoerd van Steenkiste
Jürgen Schmidhuber

Efficient exploration in reinforcement learning is a challenging problem commonly addressed through intrinsic rewards. Recent prominent approaches are based on state novelty or variants of artificial curiosity. However, directly applying them to partially observable environments can be ineffective and lead to premature dissipation of intrinsic rewards. Here we propose random curiosity with general value functions (RC-GVF), a novel intrinsic reward function that draws upon connections between these distinct approaches. Instead of using only the current observation’s novelty or a curiosity bonus for failing to predict precise environment dynamics, RC-GVF derives intrinsic rewards through predicting temporally extended general value functions. We demonstrate that this improves exploration in a hard-exploration diabolical lock problem. Furthermore, RC-GVF significantly outperforms previous methods in the absence of ground-truth episodic counts in the partially observable MiniGrid environments. Panoramic observations on MiniGrid further boost RC-GVF's performance such that it is competitive to baselines exploiting privileged information in form of episodic counts.

PDF Details

EWRL Workshop 2022 Workshop Paper

Goal-Conditioned Generators of Deep Policies

Francesco Faccio
Vincent Herrmann
Aditya Ramesh
Louis Kirsch
Jürgen Schmidhuber

Traditional Reinforcement Learning (RL) learns policies that maximize expected return. Here we study neural nets (NNs) that learn to generate policies in form of context-specific weight matrices, similar to Fast Weight Programmers and other methods from the 1990s. Using context commands of the form "generate a policy that achieves a desired expected return," our NN generators combine powerful exploration of parameter space with greedy command choices to iteratively find better and better policies. A form of weight-sharing HyperNetworks and policy embeddings scales our method to generate deep NNs. Experiments show how a single learned policy generator can produce policies that achieve any return seen during training. Finally, we evaluate our algorithm on a set of continuous control tasks where it exhibits competitive performance. Our code is public.1

PDF Details

AAAI Conference 2022 Conference Paper

Introducing Symmetries to Black Box Meta Reinforcement Learning

Louis Kirsch
Sebastian Flennerhag
Hado van Hasselt
Abram Friesen
Junhyuk Oh
Yutian Chen

Meta reinforcement learning (RL) attempts to discover new RL algorithms automatically from environment interaction. In so-called black-box approaches, the policy and the learning algorithm are jointly represented by a single neural network. These methods are very flexible, but they tend to underperform compared to human-engineered RL algorithms in terms of generalisation to new, unseen environments. In this paper, we explore the role of symmetries in meta-generalisation. We show that a recent successful meta RL approach that metalearns an objective for backpropagation-based learning exhibits certain symmetries (specifically the reuse of the learning rule, and invariance to input and output permutations) that are not present in typical black-box meta RL systems. We hypothesise that these symmetries can play an important role in meta-generalisation. Building off recent work in black-box supervised meta learning, we develop a blackbox meta RL system that exhibits these same symmetries. We show through careful experimentation that incorporating these symmetries can lead to algorithms with a greater ability to generalise to unseen action & observation spaces, tasks, and environments.

PDF Details

NeurIPS Conference 2021 Conference Paper

Meta Learning Backpropagation And Improving It

Louis Kirsch
Jürgen Schmidhuber

Many concepts have been proposed for meta learning with neural networks (NNs), e. g. , NNs that learn to reprogram fast weights, Hebbian plasticity, learned learning rules, and meta recurrent NNs. Our Variable Shared Meta Learning (VSML) unifies the above and demonstrates that simple weight-sharing and sparsity in an NN is sufficient to express powerful learning algorithms (LAs) in a reusable fashion. A simple implementation of VSML where the weights of a neural network are replaced by tiny LSTMs allows for implementing the backpropagation LA solely by running in forward-mode. It can even meta learn new LAs that differ from online backpropagation and generalize to datasets outside of the meta training distribution without explicit gradient calculation. Introspection reveals that our meta learned LAs learn through fast association in a way that is qualitatively different from gradient descent.

PDF Details

ICLR Conference 2021 Conference Paper

Parameter-Based Value Functions

Francesco Faccio
Louis Kirsch
Jürgen Schmidhuber

Traditional off-policy actor-critic Reinforcement Learning (RL) algorithms learn value functions of a single target policy. However, when value functions are updated to track the learned policy, they forget potentially useful information about old policies. We introduce a class of value functions called Parameter-Based Value Functions (PBVFs) whose inputs include the policy parameters. They can generalize across different policies. PBVFs can evaluate the performance of any policy given a state, a state-action pair, or a distribution over the RL agent's initial states. First we show how PBVFs yield novel off-policy policy gradient theorems. Then we derive off-policy actor-critic algorithms based on PBVFs trained by Monte Carlo or Temporal Difference methods. We show how learned PBVFs can zero-shot learn new policies that outperform any policy seen during training. Finally our algorithms are evaluated on a selection of discrete and continuous control tasks using shallow policies and deep neural networks. Their performance is comparable to state-of-the-art methods.

Details

ICLR Conference 2020 Conference Paper

Improving Generalization in Meta Reinforcement Learning using Learned Objectives

Louis Kirsch
Sjoerd van Steenkiste
Jürgen Schmidhuber

Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is inspired by this process. MetaGenRL distills the experiences of many complex agents to meta-learn a low-complexity neural objective function that decides how future individuals will learn. Unlike recent meta-RL algorithms, MetaGenRL can generalize to new environments that are entirely different from those used for meta-training. In some cases, it even outperforms human-engineered RL algorithms. MetaGenRL uses off-policy second-order gradients during meta-training that greatly increase its sample efficiency.

Details

NeurIPS Conference 2018 Conference Paper

Modular Networks: Learning to Decompose Neural Computation

Louis Kirsch
Julius Kunze
David Barber

Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number of parameters with a relatively small increase in resources. We propose a training algorithm that flexibly chooses neural modules based on the data to be processed. Both the decomposition and modules are learned end-to-end. In contrast to existing approaches, training does not rely on regularization to enforce diversity in module use. We apply modular networks both to image recognition and language modeling tasks, where we achieve superior performance compared to several baselines. Introspection reveals that modules specialize in interpretable contexts.

PDF Details