Author name cluster

Harm van Seijen

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.

21 papers

2 author rows

ICLR Conference 2024 Conference Paper

Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning

Mingde Zhao 0001
Safa Alver
Harm van Seijen
Romain Laroche
Doina Precup
Yoshua Bengio

Inspired by human conscious planning, we propose Skipper, a model-based reinforcement learning framework utilizing spatio-temporal abstractions to generalize better in novel situations. It automatically decomposes the given task into smaller, more manageable subtasks, and thus enables sparse decision-making and focused computation on the relevant parts of the environment. The decomposition relies on the extraction of an abstracted proxy problem represented as a directed graph, in which vertices and edges are learned end-to-end from hindsight. Our theoretical analyses provide performance guarantees under appropriate assumptions and establish where our approach is expected to be helpful. Generalization-focused experiments validate Skipper’s significant advantage in zero-shot generalization, compared to some existing state-of-the-art hierarchical planning methods.

Details

AAMAS Conference 2023 Conference Paper

One-Shot Learning from a Demonstration with Hierarchical Latent Language

Nathaniel Weir
Xingdi Yuan
Marc-Alexandre Côté
Matthew Hausknecht
Romain Laroche
Ida Momennejad
Harm van Seijen
Benjamin Van Durme

Humans have the capability, aided by the expressive compositionality of their language, to learn quickly by demonstration. They are able to describe unseen task-performing procedures and generalize their execution to other contexts. This work introduces DescribeWorld, a Minecraft-like grid world environment designed to test this sort of generalization skill in grounded agents, where tasks are linguistically and procedurally composed of elementary concepts. The agent observes a single task demonstration, and is then asked to carry out the same task in a new map. To enable such a level of generalization, we propose a neural agent infused with hierarchical latent language—at the levels of task inference and subtask planning. Through a suite of generalization tests, we find agents that perform text-based inference are better equipped for the challenge under a random split of tasks.

PDF

ICML Conference 2023 Conference Paper

Principled Offline RL in the Presence of Rich Exogenous Information

Riashat Islam
Manan Tomar
Alex Lamb
Yonathan Efroni
Hongyu Zang
Aniket Rajiv Didolkar
Dipendra Misra
Xin Li 0033

Learning to control an agent from offline data collected in a rich pixel-based visual observation space is vital for real-world applications of reinforcement learning (RL). A major challenge in this setting is the presence of input information that is hard to model and irrelevant to controlling the agent. This problem has been approached by the theoretical RL community through the lens of exogenous information, i. e. , any control-irrelevant information contained in observations. For example, a robot navigating in busy streets needs to ignore irrelevant information, such as other people walking in the background, textures of objects, or birds in the sky. In this paper, we focus on the setting with visually detailed exogenous information and introduce new offline RL benchmarks that offer the ability to study this problem. We find that contemporary representation learning techniques can fail on datasets where the noise is a complex and time-dependent process, which is prevalent in practical applications. To address these, we propose to use multi-step inverse models to learn Agent-Centric Representations for Offline-RL (ACRO). Despite being simple and reward-free, we show theoretically and empirically that the representation created by this objective greatly outperforms baselines.

Details

AAMAS Conference 2022 Conference Paper

A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms

Shangtong Zhang
Romain Laroche
Harm van Seijen
Shimon Whiteson
Remi Tachet des Combes

We investigate the discounting mismatch in actor-critic algorithm implementations from a representation learning perspective. Theoretically, actor-critic algorithms usually have discounting for both the actor and critic, i. e. , there is a γt term in the actor update for the transition observed at time t in a trajectory and the critic is a discounted value function. Practitioners, however, usually ignore the discounting (γt ) for the actor while using a discounted critic. We investigate this mismatch in two scenarios. In the first scenario, we consider optimizing an undiscounted objective (γ = 1) where γt disappears naturally (1t = 1). We then propose to interpret the discounting in the critic in terms of a bias-variance-representation trade-off and provide supporting empirical results. In the second scenario, we consider optimizing a discounted objective (γ < 1) and propose to interpret the omission of the discounting in the actor update from an auxiliary task perspective and provide supporting empirical results.

PDF

ICLR Conference 2022 Conference Paper

Modular Lifelong Reinforcement Learning via Neural Composition

Jorge A. Mendez
Harm van Seijen
Eric Eaton

Humans commonly solve complex problems by decomposing them into easier subproblems and then combining the subproblem solutions. This type of compositional reasoning permits reuse of the subproblem solutions when tackling future tasks that share part of the underlying compositional structure. In a continual or lifelong reinforcement learning (RL) setting, this ability to decompose knowledge into reusable components would enable agents to quickly learn new RL tasks by leveraging accumulated compositional structures. We explore a particular form of composition based on neural modules and present a set of RL problems that intuitively admit compositional solutions. Empirically, we demonstrate that neural composition indeed captures the underlying structure of this space of problems. We further propose a compositional lifelong RL method that leverages accumulated neural components to accelerate the learning of future tasks while retaining performance on previous tasks via off-line RL over replayed experiences.

Details

ICML Conference 2022 Conference Paper

Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods

Yi Wan
Ali Rahimi-Kalahroudi
Janarthanan Rajendran
Ida Momennejad
Sarath Chandar
Harm van Seijen

In recent years, a growing number of deep model-based reinforcement learning (RL) methods have been introduced. The interest in deep model-based RL is not surprising, given its many potential benefits, such as higher sample efficiency and the potential for fast adaption to changes in the environment. However, we demonstrate, using an improved version of the recently introduced Local Change Adaptation (LoCA) setup, that well-known model-based methods such as PlaNet and DreamerV2 perform poorly in their ability to adapt to local environmental changes. Combined with prior work that made a similar observation about the other popular model-based method, MuZero, a trend appears to emerge, suggesting that current deep model-based methods have serious limitations. We dive deeper into the causes of this poor performance, by identifying elements that hurt adaptive behavior and linking these to underlying techniques frequently used in deep model-based RL. We empirically validate these insights in the case of linear function approximation by demonstrating that a modified version of linear Dyna achieves effective adaptation to local changes. Furthermore, we provide detailed insights into the challenges of building an adaptive nonlinear model-based method, by experimenting with a nonlinear version of Dyna.

Details

ICML Conference 2021 Conference Paper

Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks

Sungryull Sohn
Sungtae Lee
Jongwook Choi
Harm van Seijen
Mehdi Fatemi
Honglak Lee

We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on the agent’s trajectory that improves the sample efficiency in sparse-reward MDPs. We show that any optimal policy necessarily satisfies the k-SP constraint. Notably, the k-SP constraint prevents the policy from exploring state-action pairs along the non-k-SP trajectories (e. g. , going back and forth). However, in practice, excluding state-action pairs may hinder the convergence of RL algorithms. To overcome this, we propose a novel cost function that penalizes the policy violating SP constraint, instead of completely excluding it. Our numerical experiment in a tabular RL setting demonstrates that the SP-constraint can significantly reduce the trajectory space of policy. As a result, our constraint enables more sample efficient learning by suppressing redundant exploration and exploitation. Our experiments on MiniGrid, DeepMind Lab, Atari, and Fetch show that the proposed method significantly improves proximal policy optimization (PPO) and outperforms existing novelty-seeking exploration methods including count-based exploration even in continuous control tasks, indicating that it improves the sample efficiency by preventing the agent from taking redundant actions.

Details

ICLR Conference 2021 Conference Paper

Systematic generalisation with group invariant predictions

Faruk Ahmed
Yoshua Bengio
Harm van Seijen
Aaron C. Courville

We consider situations where the presence of dominant simpler correlations with the target variable in a training set can cause an SGD-trained neural network to be less reliant on more persistently correlating complex features. When the non-persistent, simpler correlations correspond to non-semantic background factors, a neural network trained on this data can exhibit dramatic failure upon encountering systematic distributional shift, where the correlating background features are recombined with different objects. We perform an empirical study on three synthetic datasets, showing that group invariance methods across inferred partitionings of the training set can lead to significant improvements at such test-time situations. We also suggest a simple invariance penalty, showing with experiments on our setups that it can perform better than alternatives. We find that even without assuming access to any systematically shifted validation sets, one can still find improvements over an ERM-trained reference model.

Details

NeurIPS Conference 2020 Conference Paper

The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

Harm van Seijen
Hadi Nekoei
Evan Racah
Sarath Chandar

Deep model-based Reinforcement Learning (RL) has the potential to substantially improve the sample-efficiency of deep RL. While various challenges have long held it back, a number of papers have recently come out reporting success with deep model-based methods. This is a great development, but the lack of a consistent metric to evaluate such methods makes it difficult to compare various approaches. For example, the common single-task sample-efficiency metric conflates improvements due to model-based learning with various other aspects, such as representation learning, making it difficult to assess true progress on model-based RL. To address this, we introduce an experimental setup to evaluate model-based behavior of RL methods, inspired by work from neuroscience on detecting model-based behavior in humans and animals. Our metric based on this setup, the Local Change Adaptation (LoCA) regret, measures how quickly an RL method adapts to a local change in the environment. Our metric can identify model-based behavior, even if the method uses a poor representation and provides insight in how close a method's behavior is from optimal model-based behavior. We use our setup to evaluate the model-based behavior of MuZero on a variation of the classic Mountain Car task.

PDF Details

ICML Conference 2019 Conference Paper

Dead-ends and Secure Exploration in Reinforcement Learning

Mehdi Fatemi
Shikhar Sharma 0001
Harm van Seijen
Samira Ebrahimi Kahou

Many interesting applications of reinforcement learning (RL) involve MDPs that include numerous “dead-end" states. Upon reaching a dead-end state, the agent continues to interact with the environment in a dead-end trajectory before reaching an undesired terminal state, regardless of whatever actions are chosen. The situation is even worse when existence of many dead-end states is coupled with distant positive rewards from any initial state (we term this as Bridge Effect). Hence, conventional exploration techniques often incur prohibitively many training steps before convergence. To deal with the bridge effect, we propose a condition for exploration, called security. We next establish formal results that translate the security condition into the learning problem of an auxiliary value function. This new value function is used to cap “any" given exploration policy and is guaranteed to make it secure. As a special case, we use this theory and introduce secure random-walk. We next extend our results to the deep RL settings by identifying and addressing two main challenges that arise. Finally, we empirically compare secure random-walk with standard benchmarks in two sets of experiments including the Atari game of Montezuma’s Revenge.

Details

NeurIPS Conference 2019 Conference Paper

Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning

Harm van Seijen
Mehdi Fatemi
Arash Tavakoli

In an effort to better understand the different ways in which the discount factor affects the optimization process in reinforcement learning, we designed a set of experiments to study each effect in isolation. Our analysis reveals that the common perception that poor performance of low discount factors is caused by (too) small action-gaps requires revision. We propose an alternative hypothesis that identifies the size-difference of the action-gap across the state-space as the primary cause. We then introduce a new method that enables more homogeneous action-gaps by mapping value estimates to a logarithmic space. We prove convergence for this method under standard assumptions and demonstrate empirically that it indeed enables lower discount factors for approximate reinforcement-learning methods. This in turn allows tackling a class of reinforcement-learning problems that are challenging to solve with traditional methods.

PDF Details

AAAI Conference 2018 Conference Paper

On Value Function Representation of Long Horizon Problems

Lucas Lehnert
Romain Laroche
Harm van Seijen

In Reinforcement Learning, an intelligent agent has to make a sequence of decisions to accomplish a goal. If this sequence is long, then the agent has to plan over a long horizon. While learning the optimal policy and its value function is a well studied problem in Reinforcement Learning, this paper focuses on the structure of the optimal value function and how hard it is to represent the optimal value function. We show that the generalized Rademacher complexity of the hypothesis space of all optimal value functions is dependent on the planning horizon and independent of the state and action space size. Further, we present bounds on the action-gaps of action value functions and show that they can collapse if a long planning horizon is used. The theoretical results are veriﬁed empirically on randomly generated MDPs and on a gridworld fruit collection task using deep value function approximation. Our theoretical results highlight a connection between value function approximation and the Options framework and suggest that value functions should be decomposed along bottlenecks of the MDP’s transition dynamics.

PDF Details

AAMAS Conference 2017 Conference Paper

Forward Actor-Critic for Nonlinear Function Approximation in Reinforcement Learning

Vivek Veeriah
Harm van Seijen
Richard S. Sutton

Multi-step methods are important in reinforcement learning (RL). Eligibility traces, the usual way of handling them, works well with linear function approximators. Recently, van Seijen (2016) had introduced a delayed learning approach, without eligibility traces, for handling the multi-step λ-return with nonlinear function approximators. However, this was limited to action-value methods. In this paper, we extend this approach to handle n-step returns, generalize this approach to policy gradient methods and empirically study the effect of such delayed updates in control tasks. Specifically, we introduce two novel forward actorcritic methods and empirically investigate our proposed methods with the conventional actor-critic method on mountain car and pole-balancing tasks. From our experiments, we observe that forward actor-critic dramatically outperforms the conventional actor-critic in these standard control tasks. Notably, this forward actor-critic method has produced a new class of multi-step RL algorithms without eligibility traces.

PDF

NeurIPS Conference 2017 Conference Paper

Hybrid Reward Architecture for Reinforcement Learning

Harm van Seijen
Mehdi Fatemi
Joshua Romoff
Romain Laroche
Tavian Barnes
Jeffrey Tsang

One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dimensional representation using a deep network. While this approach works well in many domains, in domains where the optimal value function cannot easily be reduced to a low-dimensional representation, learning can be very slow and unstable. This paper contributes towards tackling such challenging domains, by proposing a new method, called Hybrid Reward Architecture (HRA). HRA takes as input a decomposed reward function and learns a separate value function for each component reward function. Because each component typically only depends on a subset of all features, the corresponding value function can be approximated more easily by a low-dimensional representation, enabling more effective learning. We demonstrate HRA on a toy-problem and the Atari game Ms. Pac-Man, where HRA achieves above-human performance.

PDF Details

RLDM Conference 2017 Conference Abstract

Separation of Concerns in Reinforcement Learning

Harm van Seijen
Mehdi Fatemi
Joshua Romoff

In this paper, we propose a model for solving a single-agent task by using multiple agents, each focusing on a different aspect of the task. This approach has two main advantages: 1) it allows for training specialized agents on different parts of the task, and 2) it provides a new way to transfer knowledge, by transferring trained agents. Our model generalizes the traditional hierarchical decomposition, where agents are organized in a hierarchical way. We validate our model empirically, by showing that it can beat a single- agent state-of-the-art method on a challenging domain.

PDF Details

JMLR Journal 2016 Journal Article

True Online Temporal-Difference Learning

Harm van Seijen
A. Rupam Mahmood
Patrick M. Pilarski
Marlos C. Machado
Richard S. Sutton

The temporal-difference methods TD($\lambda$) and Sarsa($\lambda$) form a core part of modern reinforcement learning. Their appeal comes from their good performance, low computational cost, and their simple interpretation, given by their forward view. Recently, new versions of these methods were introduced, called true online TD($\lambda$) and true online Sarsa($\lambda$), respectively (van Seijen & Sutton, 2014). Algorithmically, these true online methods only make two small changes to the update rules of the regular methods, and the extra computational cost is negligible in most cases. However, they follow the ideas underlying the forward view much more closely. In particular, they maintain an exact equivalence with the forward view at all times, whereas the traditional versions only approximate it for small step-sizes. We hypothesize that these true online methods not only have better theoretical properties, but also dominate the regular methods empirically. In this article, we put this hypothesis to the test by performing an extensive empirical comparison. Specifically, we compare the performance of true online TD($\lambda$)/Sarsa($\lambda$) with regular TD($\lambda$)/Sarsa($\lambda$) on random MRPs, a real-world myoelectric prosthetic arm, and a domain from the Arcade Learning Environment. We use linear function approximation with tabular, binary, and non-binary features. Our results suggest that the true online methods indeed dominate the regular methods. Across all domains/representations the learning speed of the true online methods are often better, but never worse than that of the regular methods. An additional advantage is that no choice between traces has to be made for the true online methods. Besides the empirical results, we provide an in-dept analysis of the theory behind true online temporal-difference learning. In addition, we show that new true online temporal- difference methods can be derived by making changes to the online forward view and then rewriting the update equations. [abs] [ pdf ][ bib ] &copy JMLR 2016. ( edit, beta )

PDF Details

RLDM Conference 2015 Conference Abstract

A Deeper Look at Planning as Learning from Replay

Harm van Seijen
Richard Sutton

In reinforcement learning, the notions of experience replay, and of planning as learning from replayed experience, have long been used to find good policies with minimal training data. Replay can be seen either as model-based reinforcement learning, where the store of past experiences serves as the model, or as a way to avoid a conventional model of the environment altogether. In this paper, we look more deeply at how replay blurs the line between model-based and model-free methods. Specifically, we show for the first time an exact equivalence between the sequence of value functions found by a model- based policy-evaluation method and by a model-free method with replay. We then use insights gained from these relationships to design a new reinforcement learning algorithm for linear function approximation. This method, which we call forgetful LSTD(λ), improves upon regular LSTD(λ) because it extends more naturally to online control, and improves upon linear Dyna because it is a multi-step method, enabling it to perform well even in non-Markov problems or, equivalently, in problems with significant function approximation.

PDF Details

EWRL Workshop 2015 Workshop Paper

An Empirical Evaluation of True-Online TD(lambda)

Harm van Seijen
Rich Sutton
Rupam Mahmood
Patrick Pilarski

The true online TD(λ) algorithm has recently been proposed (van Seijen and Sutton, 2014) as a universal replacement for the popular TD(λ) algorithm, in temporal-difference learning and reinforcement learning. True online TD(λ) has better theoretical properties than conventional TD(λ), and the expectation is that it also results in faster learning. In this paper, we put this hypothesis to the test. Specifically, we compare the performance of true online TD(λ) with that of TD(λ) on challenging examples, random Markov reward processes, and a real-world myoelectric prosthetic arm. We use linear function approximation with tabular, binary, and non-binary features. We assess the algorithms along three dimensions: computational cost, learning speed, and ease of use. Our results confirm the strength of true online TD(λ): 1) for sparse feature vectors, the computational overhead with respect to TD(λ) is minimal; for non-sparse features the computation time is at most twice that of TD(λ), 2) across all domains/representations the learning speed of true online TD(λ) is often better, but never worse than that of TD(λ), and 3) true online TD(λ) is easier to use, because it does not require choosing between trace types, and it is generally more stable with respect to the step-size. Overall, our results suggest that true online TD(λ) should be the first choice when looking for an efficient, general-purpose TD method.

Details

ICML Conference 2014 Conference Paper

True Online TD(lambda)

Harm van Seijen
Richard S. Sutton

TD(lambda) is a core algorithm of modern reinforcement learning. Its appeal comes from its equivalence to a clear and conceptually simple forward view, and the fact that it can be implemented online in an inexpensive manner. However, the equivalence between TD(lambda) and the forward view is exact only for the off-line version of the algorithm (in which updates are made only at the end of each episode). In the online version of TD(lambda) (in which updates are made at each step, which generally performs better and is always used in applications) the match to the forward view is only approximate. In a sense this is unavoidable for the conventional forward view, as it itself presumes that the estimates are unchanging during an episode. In this paper we introduce a new forward view that takes into account the possibility of changing estimates and a new variant of TD(lambda) that exactly achieves it. Our algorithm uses a new form of eligibility trace similar to but different from conventional accumulating and replacing traces. The overall computational complexity is the same as TD(lambda), even when using function approximation. In our empirical comparisons, our algorithm outperformed TD(lambda) in all of its variations. It seems, by adhering more truly to the original goal of TD(lambda)—matching an intuitively clear forward view even in the online case—that we have found a new algorithm that simply improves on classical TD(lambda).

Details

ICML Conference 2013 Conference Paper

Planning by Prioritized Sweeping with Small Backups

Harm van Seijen
Richard S. Sutton

Efficient planning plays a crucial role in model-based reinforcement learning. Traditionally, the main planning operation is a full backup based on the current estimates of the successor states. Consequently, its computation time is proportional to the number of successor states. In this paper, we introduce a new planning backup that uses only the current value of a single successor state and has a computation time independent of the number of successor states. This new backup, which we call a small backup, opens the door to a new class of model-based reinforcement learning methods that exhibit much finer control over their planning process than traditional methods. We empirically demonstrate that this increased flexibility allows for more efficient planning by showing that an implementation of prioritized sweeping based on small backups achieves a substantial performance improvement over classical implementations.

Details

JMLR Journal 2011 Journal Article

Exploiting Best-Match Equations for Efficient Reinforcement Learning

Harm van Seijen
Shimon Whiteson
Hado van Hasselt
Marco Wiering

This article presents and evaluates best-match learning, a new approach to reinforcement learning that trades off the sample efficiency of model-based methods with the space efficiency of model-free methods. Best-match learning works by approximating the solution to a set of best-match equations, which combine a sparse model with a model-free Q-value function constructed from samples not used by the model. We prove that, unlike regular sparse model-based methods, best-match learning is guaranteed to converge to the optimal Q-values in the tabular case. Empirical results demonstrate that best-match learning can substantially outperform regular sparse model-based methods, as well as several model-free methods that strive to improve the sample efficiency of temporal-difference methods. In addition, we demonstrate that best-match learning can be successfully combined with function approximation. [abs] [ pdf ][ bib ] &copy JMLR 2011. ( edit, beta )

PDF Details