David Abel

David Abel, André Barreto, Benjamin Van Roy et al. · deepmind, stanford

In a standard view of the reinforcement learning problem, an agent's goal is to efficiently identify a policy that maximizes long-term reward. However, this perspective is based on a restricted view of learning as finding a solution, rather than treating learning as endless adaptation. In contrast, continual reinforcement learning refers to the setting in which the best agents never stop learning. Despite the importance of continual reinforcement learning, the community lacks a simple definition of the problem that highlights its commitments and makes its primary concepts precise and clear. To this end, this paper is dedicated to carefully defining the continual reinforcement learning problem. We formalize the notion of agents that "never stop learning" through a new mathematical language for analyzing and cataloging agents. Using this new language, we define a continual learning agent as one that can be understood as carrying out an implicit search process indefinitely, and continual reinforcement learning as the setting in which the best agents are all continual learning agents. We provide two motivating examples, illustrating that traditional views of multi-task reinforcement learning and continual supervised learning are special cases of our definition. Collectively, these definitions and perspectives formalize many intuitive concepts at the heart of learning, and open new research pathways surrounding continual learning agents.

Michael Bowling, John D. Martin, David Abel et al. · deepmind

The reward hypothesis posits that, "all of what we mean by goals and purposes can be well thought of as maximization of the expected value of the cumulative sum of a received scalar signal (reward)." We aim to fully settle this hypothesis. This will not conclude with a simple affirmation or refutation, but rather specify completely the implicit requirements on goals and purposes under which the hypothesis holds.

David Abel, André Barreto, Hado van Hasselt et al. · deepmind, stanford

When has an agent converged? Standard models of the reinforcement learning problem give rise to a straightforward definition of convergence: An agent converges when its behavior or performance in each environment state stops changing. However, as we shift the focus of our learning problem from the environment's state to the agent's state, the concept of an agent's convergence becomes significantly less clear. In this paper, we propose two complementary accounts of agent convergence in a framing of the reinforcement learning problem that centers around bounded agents. The first view says that a bounded agent has converged when the minimal number of states needed to describe the agent's future behavior cannot decrease. The second view says that a bounded agent has converged just when the agent's performance only changes if the agent's internal state changes. We establish basic properties of these two definitions, show that they accommodate typical views of convergence in standard settings, and prove several facts about their nature and relationship. We take these perspectives, definitions, and analysis to bring clarity to a central idea of the field.

David Abel · deepmind

Reinforcement learning defines the problem facing agents that learn to make good decisions through action and observation alone. To be effective problem solvers, such agents must efficiently explore vast worlds, assign credit from delayed feedback, and generalize to new experiences, all while making use of limited data, computational resources, and perceptual bandwidth. Abstraction is essential to all of these endeavors. Through abstraction, agents can form concise models of their environment that support the many practices required of a rational, adaptive decision maker. In this dissertation, I present a theory of abstraction in reinforcement learning. I first offer three desiderata for functions that carry out the process of abstraction: they should 1) preserve representation of near-optimal behavior, 2) be learned and constructed efficiently, and 3) lower planning or learning time. I then present a suite of new algorithms and analysis that clarify how agents can learn to abstract according to these desiderata. Collectively, these results provide a partial path toward the discovery and use of abstraction that minimizes the complexity of effective reinforcement learning.

Jelena Luketina, Sebastian Flennerhag, Yannick Schroecker et al. · deepmind

Meta-gradient methods (Xu et al., 2018; Zahavy et al., 2020) offer a promising solution to the problem of hyperparameter selection and adaptation in non-stationary reinforcement learning problems. However, the properties of meta-gradients in such environments have not been systematically studied. In this work, we bring new clarity to meta-gradients in non-stationary environments. Concretely, we ask: (i) how much information should be given to the learned optimizers, so as to enable faster adaptation and generalization over a lifetime, (ii) what meta-optimizer functions are learned in this process, and (iii) whether meta-gradient methods provide a bigger advantage in highly non-stationary environments. To study the effect of information provided to the meta-optimizer, as in recent works (Flennerhag et al., 2021; Almeida et al., 2021), we replace the tuned meta-parameters of fixed update rules with learned meta-parameter functions of selected context features. The context features carry information about agent performance and changes in the environment and hence can inform learned meta-parameter schedules. We find that adding more contextual information is generally beneficial, leading to faster adaptation of meta-parameter values and increased performance over a lifetime. We support these results with a qualitative analysis of resulting meta-parameter schedules and learned functions of context features. Lastly, we find that without context, meta-gradients do not provide a consistent advantage over the baseline in highly non-stationary environments. Our findings suggest that contextualizing meta-gradients can play a pivotal role in extracting high performance from meta-gradients in non-stationary settings.

David Abel, Mark K. Ho, Anna Harutyunyan · deepmind

Modern reinforcement learning has been conditioned by at least three dogmas. The first is the environment spotlight, which refers to our tendency to focus on modeling environments rather than agents. The second is our treatment of learning as finding the solution to a task, rather than adaptation. The third is the reward hypothesis, which states that all goals and purposes can be well thought of as maximization of a reward signal. These three dogmas shape much of what we think of as the science of reinforcement learning. While each of the dogmas have played an important role in developing the field, it is time we bring them to the surface and reflect on whether they belong as basic ingredients of our scientific paradigm. In order to realize the potential of reinforcement learning as a canonical frame for researching intelligent agents, we suggest that it is time we shed dogmas one and two entirely, and embrace a nuanced approach to the third.

Kale-ab Tessera, Leonard Hinckeldey, Riccardo Zamboni et al.

Cooperative multi-agent reinforcement learning (MARL) is typically framed as a decentralised partially observable Markov decision process (Dec-POMDP), a setting whose hardness stems from two key challenges: partial observability and decentralised coordination. Genuinely solving such tasks requires Dec-POMDP reasoning, where agents use history to infer hidden states and coordinate based on local information. Yet it remains unclear whether popular benchmarks actually demand this reasoning or permit success via simpler strategies. We introduce a diagnostic suite combining statistically grounded performance comparisons and information-theoretic probes to audit the behavioural complexity of baseline policies (IPPO and MAPPO) across 37 scenarios spanning MPE, SMAX, Overcooked, Hanabi, and MaBrax. Our diagnostics reveal that success on these benchmarks rarely requires genuine Dec-POMDP reasoning. Reactive policies match the performance of memory-based agents in over half the scenarios, and emergent coordination frequently relies on brittle, synchronous action coupling rather than robust temporal influence. These findings suggest that some widely used benchmarks may not adequately test core Dec-POMDP assumptions under current training paradigms, potentially leading to over-optimistic assessments of progress. We release our diagnostic tooling to support more rigorous environment design and evaluation in cooperative MARL.

Ben Sanati, Thomas L. Lee, Trevor McInroe et al.

A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge when adapting to new data. Addressing this problem requires a principled understanding of forgetting; yet, despite decades of study, no unified definition has emerged that provides insights into the underlying dynamics of learning. We propose an algorithm- and task-agnostic theory that characterises forgetting as a lack of self-consistency in a learner's predictive distribution over future experiences, manifesting as a loss of predictive information. Our theory naturally yields a general measure of an algorithm's propensity to forget. To validate the theory, we design a comprehensive set of experiments that span classification, regression, generative modelling, and reinforcement learning. We empirically demonstrate how forgetting is present across all learning settings and plays a significant role in determining learning efficiency. Together, these results establish a principled understanding of forgetting and lay the foundation for analysing and improving the information retention capabilities of general learning algorithms.

Hyunin Lee, Chanwoo Park, David Abel et al.

Black swan events are statistically rare occurrences that carry extremely high risks. A typical view of defining black swan events is heavily assumed to originate from an unpredictable time-varying environments; however, the community lacks a comprehensive definition of black swan events. To this end, this paper challenges that the standard view is incomplete and claims that high-risk, statistically rare events can also occur in unchanging environments due to human misperception of their value and likelihood, which we call as spatial black swan event. We first carefully categorize black swan events, focusing on spatial black swan events, and mathematically formalize the definition of black swan events. We hope these definitions can pave the way for the development of algorithms to prevent such events by rationally correcting human perception.

Elle Miller, Jayaram Reddy, Ayush Deshmukh et al.

Tactile-based reinforcement learning (RL) is currently hindered by fragmented research and a focus on over-saturated orientation tasks. We introduce v2 of the Robot Tactile Olympiad (\texttt{roto 2.0}), a GPU-parallelised benchmark designed to standardise tactile-based RL across four distinct robotic morphologies (16-DOF to 24-DOF). Unlike prior benchmarks, roto focuses on end-to-end "blind" manipulation, utilising only proprioception and tactile sensing without state information or distillation. We demonstrate a significant performance leap, with our blind agents achieving 13 Baoding ball rotations in 10 seconds, an order of magnitude faster than current state-of-the-art speeds. By open-sourcing our environments and robustly tuned baselines, we reduce the barrier to entry and enable researchers to prioritise fundamental algorithmic challenges over tedious RL tuning. Website: https://elle-miller.github.io/roto/

Samuel Garcin, Trevor McInroe, Pablo Samuel Castro et al.

Extracting relevant information from a stream of high-dimensional observations is a central challenge for deep reinforcement learning agents. Actor-critic algorithms add further complexity to this challenge, as it is often unclear whether the same information will be relevant to both the actor and the critic. To this end, we here explore the principles that underlie effective representations for the actor and for the critic in on-policy algorithms. We focus our study on understanding whether the actor and critic will benefit from separate, rather than shared, representations. Our primary finding is that when separated, the representations for the actor and critic systematically specialise in extracting different types of information from the environment -- the actor's representation tends to focus on action-relevant information, while the critic's representation specialises in encoding value and dynamics information. We conduct a rigourous empirical study to understand how different representation learning approaches affect the actor and critic's specialisations and their downstream performance, in terms of sample efficiency and generation capabilities. Finally, we discover that a separated critic plays an important role in exploration and data collection during training. Our code, trained models and data are accessible at https://github.com/francelico/deac-rep.

Logan Mondal Bhamidipaty, Esmeralda S. Whitammer, David Abel et al.

We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy should be strictly preferred over another while the environment's true transition model implies the reverse. We analogize our definition with a prior characterization of reward hacking but show that the associated proof of inevitability does not transfer to exploitation. To overcome this obstruction, we develop a general theory of reward hacking and model exploitation that proves that exploitation is essentially unavoidable on large policy sets and yields the corresponding claim for hacking as a special case. Unfortunately, we also find that the conditions that guarantee unhackability in finite policy sets have no counterpart that precludes exploitation. Consequently, we introduce a relaxed notion of exploitation and derive a safe horizon within which it can be avoided. Taken together, our results establish a formal bridge between reward hacking and model exploitation and elucidate the limits of safe planning in world models.

Raul D. Steleac, Mohan Sridharan, David Abel

Temporally extended actions improve the ability to explore and plan in single-agent settings. In multi-agent settings, the exponential growth of the joint state space with the number of agents makes coordinated behaviours even more valuable. Yet, this same exponential growth renders the design of multi-agent options particularly challenging. Existing multi-agent option discovery methods often sacrifice coordination by producing loosely coupled or fully independent behaviours. Toward addressing these limitations, we describe a novel approach for multi-agent option discovery. Specifically, we propose a joint-state abstraction that compresses the state space while preserving the information necessary to discover strongly coordinated behaviours. Our approach builds on the inductive bias that synchronisation over agent states provides a natural foundation for coordination in the absence of explicit objectives. We first approximate a fictitious state of maximal alignment with the team, the \textit{Fermat} state, and use it to define a measure of \textit{spreadness}, capturing team-level misalignment on each individual state dimension. Building on this representation, we then employ a neural graph Laplacian estimator to derive options that capture state synchronisation patterns between agents. We evaluate the resulting options across multiple scenarios in two multi-agent domains, showing that they yield stronger downstream coordination capabilities compared to alternative option discovery methods.

Alper Demir, Hüseyin Aydın, Kale-ab Abebe Tessera et al.

Sequential Social Dilemmas (SSDs) provide a key framework for studying how cooperation emerges when individual incentives conflict with collective welfare. In Multi-Agent Reinforcement Learning, these problems are often addressed by incorporating intrinsic drives that encourage prosocial or fair behavior. However, most existing methods assume that agents face identical incentives in the dilemma and require continuous access to global information about other agents to assess fairness. In this work, we introduce asymmetric variants of well-known SSD environments and examine how natural differences between agents influence cooperation dynamics. Our findings reveal that existing fairness-based methods struggle to adapt under asymmetric conditions by enforcing raw equality that wrongfully incentivize defection. To address this, we propose three modifications: (i) redefining fairness by accounting for agents' reward ranges, (ii) introducing an agent-based weighting mechanism to better handle inherent asymmetries, and (iii) localizing social feedback to make the methods effective under partial observability without requiring global information sharing. Experimental results show that in asymmetric scenarios, our method fosters faster emergence of cooperative policies compared to existing approaches, without sacrificing scalability or practicality.

Jonathan Richens, David Abel, Alexis Bellot et al.

Are world models a necessary ingredient for flexible, goal-directed behaviour, or is model-free learning sufficient? We provide a formal answer to this question, showing that any agent capable of generalizing to multi-step goal-directed tasks must have learned a predictive model of its environment. We show that this model can be extracted from the agent's policy, and that increasing the agents performance or the complexity of the goals it can achieve requires learning increasingly accurate world models. This has a number of consequences: from developing safe and general agents, to bounding agent capabilities in complex environments, and providing new algorithms for eliciting world models from agents.

Andi Peng, Yuying Sun, Tianmin Shu et al.

Humans use social context to specify preferences over behaviors, i.e. their reward functions. Yet, algorithms for inferring reward models from preference data do not take this social learning view into account. Inspired by pragmatic human communication, we study how to extract fine-grained data regarding why an example is preferred that is useful for learning more accurate reward models. We propose to enrich binary preference queries to ask both (1) which features of a given example are preferable in addition to (2) comparisons between examples themselves. We derive an approach for learning from these feature-level preferences, both for cases where users specify which features are reward-relevant, and when users do not. We evaluate our approach on linear bandit settings in both vision- and language-based domains. Results support the efficiency of our approach in quickly converging to accurate rewards with fewer comparisons vs. example-only labels. Finally, we validate the real-world applicability with a behavioral experiment on a mushroom foraging task. Our findings suggest that incorporating pragmatic feature preferences is a promising approach for more efficient user-aligned reward learning.

Bernardo Ávila Pires, Mark Rowland, Diana Borsa et al.

We introduce distributional dynamic programming (DP) methods for optimizing statistical functionals of the return distribution, with standard reinforcement learning as a special case. Previous distributional DP methods could optimize the same class of expected utilities as classic DP. To go beyond, we combine distributional DP with stock augmentation, a technique previously introduced for classic DP in the context of risk-sensitive RL, where the MDP state is augmented with a statistic of the rewards obtained since the first time step. We find that a number of recently studied problems can be formulated as stock-augmented return distribution optimization, and we show that we can use distributional DP to solve them. We analyze distributional value and policy iteration, with bounds and a study of what objectives these distributional DP methods can or cannot optimize. We describe a number of applications outlining how to use distributional DP to solve different stock-augmented return distribution optimization problems, for example maximizing conditional value-at-risk, and homeostatic regulation. To highlight the practical potential of stock-augmented return distribution optimization and distributional DP, we introduce an agent that combines DQN and the core ideas of distributional DP, and empirically evaluate it for solving instances of the applications discussed.

David Abel, André Barreto, Michael Bowling et al. · deepmind

Agency is a system's capacity to steer outcomes toward a goal, and is a central topic of study across biology, philosophy, cognitive science, and artificial intelligence. Determining if a system exhibits agency is a notoriously difficult question: Dennett (1989), for instance, highlights the puzzle of determining which principles can decide whether a rock, a thermostat, or a robot each possess agency. We here address this puzzle from the viewpoint of reinforcement learning by arguing that agency is fundamentally frame-dependent: Any measurement of a system's agency must be made relative to a reference frame. We support this claim by presenting a philosophical argument that each of the essential properties of agency proposed by Barandiaran et al. (2009) and Moreno (2018) are themselves frame-dependent. We conclude that any basic science of agency requires frame-dependence, and discuss the implications of this claim for reinforcement learning.

David Abel, Michael Bowling, André Barreto et al. · deepmind

Agents are minimally entities that are influenced by their past observations and act to influence future observations. This latter capacity is captured by empowerment, which has served as a vital framing concept across artificial intelligence and cognitive science. This former capacity, however, is equally foundational: In what ways, and to what extent, can an agent be influenced by what it observes? In this paper, we ground this concept in a universal agent-centric measure that we refer to as plasticity, and reveal a fundamental connection to empowerment. Following a set of desiderata on a suitable definition, we define plasticity using a new information-theoretic quantity we call the generalized directed information. We show that this new quantity strictly generalizes the directed information introduced by Massey (1990) while preserving all of its desirable properties. Under this definition, we find that plasticity is well thought of as the mirror of empowerment: The two concepts are defined using the same measure, with only the direction of influence reversed. Our main result establishes a tension between the plasticity and empowerment of an agent, suggesting that agent design needs to be mindful of both characteristics. We explore the implications of these findings, and suggest that plasticity, empowerment, and their relationship are essential to understanding agency

Elle Miller, Trevor McInroe, David Abel et al.

Achieving safe, reliable real-world robotic manipulation requires agents to evolve beyond vision and incorporate tactile sensing to overcome sensory deficits and reliance on idealised state information. Despite its potential, the efficacy of tactile sensing in reinforcement learning (RL) remains inconsistent. We address this by developing self-supervised learning (SSL) methodologies to more effectively harness tactile observations, focusing on a scalable setup of proprioception and sparse binary contacts. We empirically demonstrate that sparse binary tactile signals are critical for dexterity, particularly for interactions that proprioceptive control errors do not register, such as decoupled robot-object motions. Our agents achieve superhuman dexterity in complex contact tasks (ball bouncing and Baoding ball rotation). Furthermore, we find that decoupling the SSL memory from the on-policy memory can improve performance. We release the Robot Tactile Olympiad (RoTO) benchmark to standardise and promote future research in tactile-based manipulation. Project page: https://elle-miller.github.io/tactile_rl

Kale-ab Abebe Tessera, Leonard Hinckeldey, Riccardo Zamboni et al.

Cooperative multi-agent reinforcement learning (MARL) is typically formalised as a Decentralised Partially Observable Markov Decision Process (Dec-POMDP), where agents must reason about the environment and other agents' behaviour. In practice, current model-free MARL algorithms use simple recurrent function approximators to address the challenge of reasoning about others using partial information. In this position paper, we argue that the empirical success of these methods is not due to effective Markov signal recovery, but rather to learning simple conventions that bypass environment observations and memory. Through a targeted case study, we show that co-adapting agents can learn brittle conventions, which then fail when partnered with non-adaptive agents. Crucially, the same models can learn grounded policies when the task design necessitates it, revealing that the issue is not a fundamental limitation of the learning models but a failure of the benchmark design. Our analysis also suggests that modern MARL environments may not adequately test the core assumptions of Dec-POMDPs. We therefore advocate for new cooperative environments built upon two core principles: (1) behaviours grounded in observations and (2) memory-based reasoning about other agents, ensuring success requires genuine skill rather than fragile, co-adapted agreements.

Massimiliano Tamborski, David Abel

Resource constraints can fundamentally change both learning and decision-making. We explore how memory constraints influence an agent's performance when navigating unknown environments using standard reinforcement learning algorithms. Specifically, memory-constrained agents face a dilemma: how much of their limited memory should be allocated to each of the agent's internal processes, such as estimating a world model, as opposed to forming a plan using that model? We study this dilemma in MCTS- and DQN-based algorithms and examine how different allocations of memory impact performance in episodic and continual learning settings.

David Abel, Will Dabney, Anna Harutyunyan et al.

Reward is the driving force for reinforcement-learning agents. This paper is dedicated to understanding the expressivity of reward as a way to capture tasks that we would want an agent to perform. We frame this study around three new abstract notions of "task" that might be desirable: (1) a set of acceptable behaviors, (2) a partial ordering over behaviors, or (3) a partial ordering over trajectories. Our main results prove that while reward can express many of these tasks, there exist instances of each task type that no Markov reward function can capture. We then provide a set of polynomial-time algorithms that construct a Markov reward function that allows an agent to optimize tasks of each of these three types, and correctly determine when no such reward function exists. We conclude with an empirical study that corroborates and illustrates our theoretical findings.

David Abel, Cameron Allen, Dilip Arumugam et al.

Reinforcement learning is hard in general. Yet, in many specific environments, learning is easy. What makes learning easy in one environment, but difficult in another? We address this question by proposing a simple measure of reinforcement-learning hardness called the bad-policy density. This quantity measures the fraction of the deterministic stationary policy space that is below a desired threshold in value. We prove that this simple quantity has many properties one would expect of a measure of learning hardness. Further, we prove it is NP-hard to compute the measure in general, but there are paths to polynomial-time approximation. We conclude by summarizing potential directions and uses for this measure.

Mark K. Ho, David Abel, Carlos G. Correa et al.

One of the most striking features of human cognition is the capacity to plan. Two aspects of human planning stand out: its efficiency and flexibility. Efficiency is especially impressive because plans must often be made in complex environments, and yet people successfully plan solutions to myriad everyday problems despite having limited cognitive resources. Standard accounts in psychology, economics, and artificial intelligence have suggested human planning succeeds because people have a complete representation of a task and then use heuristics to plan future actions in that representation. However, this approach generally assumes that task representations are fixed. Here, we propose that task representations can be controlled and that such control provides opportunities to quickly simplify problems and more easily reason about them. We propose a computational account of this simplification process and, in a series of pre-registered behavioral experiments, show that it is subject to online cognitive control and that people optimally balance the complexity of a task representation and its utility for planning and acting. These results demonstrate how strategically perceiving and conceiving problems facilitates the effective use of limited cognitive resources.

Tadashi Kozuno, Yunhao Tang, Mark Rowland et al.

Off-policy multi-step reinforcement learning algorithms consist of conservative and non-conservative algorithms: the former actively cut traces, whereas the latter do not. Recently, Munos et al. (2016) proved the convergence of conservative algorithms to an optimal Q-function. In contrast, non-conservative algorithms are thought to be unsafe and have a limited or no theoretical guarantee. Nonetheless, recent studies have shown that non-conservative algorithms empirically outperform conservative ones. Motivated by the empirical results and the lack of theory, we carry out theoretical analyses of Peng's Q($λ$), a representative example of non-conservative algorithms. We prove that it also converges to an optimal policy provided that the behavior policy slowly tracks a greedy policy in a way similar to conservative policy iteration. Such a result has been conjectured to be true but has not been proven. We also experiment with Peng's Q($λ$) in complex continuous control tasks, confirming that Peng's Q($λ$) often outperforms conservative algorithms despite its simplicity. These results indicate that Peng's Q($λ$), which was thought to be unsafe, is a theoretically-sound and practically effective algorithm.

Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici et al.

Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the features of their environment and the actions that are feasible. Gibson (1977) coined the term "affordances" to describe the fact that certain states enable an agent to do certain actions, in the context of embodied agents. In this paper, we develop a theory of affordances for agents who learn and plan in Markov Decision Processes. Affordances play a dual role in this case. On one hand, they allow faster planning, by reducing the number of actions available in any given situation. On the other hand, they facilitate more efficient and precise learning of transition models from data, especially when such models require function approximation. We establish these properties through theoretical results as well as illustrative examples. We also propose an approach to learn affordances and use it to estimate transition models that are simpler and generalize better.

Mark K. Ho, David Abel, Jonathan D. Cohen et al.

Planning is useful. It lets people take actions that have desirable long-term consequences. But, planning is hard. It requires thinking about consequences, which consumes limited computational and cognitive resources. Thus, people should plan their actions, but they should also be smart about how they deploy resources used for planning their actions. Put another way, people should also "plan their plans". Here, we formulate this aspect of planning as a meta-reasoning problem and formalize it in terms of a recursive Bellman objective that incorporates both task rewards and information-theoretic planning costs. Our account makes quantitative predictions about how people should plan and meta-plan as a function of the overall structure of a task, which we test in two experiments with human participants. We find that people's reaction times reflect a planned use of information processing, consistent with our account. This formulation of planning to plan provides new insight into the function of hierarchical planning, state abstraction, and cognitive control in both humans and machines.

Kavosh Asadi, David Abel, Michael L. Littman

Can simple algorithms with a good representation solve challenging reinforcement learning problems? In this work, we answer this question in the affirmative, where we take "simple learning algorithm" to be tabular Q-Learning, the "good representations" to be a learned state abstraction, and "challenging problems" to be continuous control tasks. Our main contribution is a learning algorithm that abstracts a continuous state-space into a discrete one. We transfer this learned representation to unseen problems to enable effective learning. We provide theory showing that learned abstractions maintain a bounded value loss, and we report experiments showing that the abstractions empower tabular Q-Learning to learn efficiently in unseen tasks.

Erwan Lecarpentier, David Abel, Kavosh Asadi et al.

We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks. We introduce a novel metric between Markov Decision Processes (MDPs) and establish that close MDPs have close optimal value functions. Formally, the optimal value functions are Lipschitz continuous with respect to the tasks space. These theoretical results lead us to a value-transfer method for Lifelong RL, which we use to build a PAC-MDP algorithm with improved convergence rate. Further, we show the method to experience no negative transfer with high probability. We illustrate the benefits of the method in Lifelong RL experiments.

Yuu Jinnai, Jee Won Park, David Abel et al.

One of the main challenges in reinforcement learning is solving tasks with sparse reward. We show that the difficulty of discovering a distant rewarding state in an MDP is bounded by the expected cover time of a random walk over the graph induced by the MDP's transition dynamics. We therefore propose to accelerate exploration by constructing options that minimize cover time. The proposed algorithm finds an option which provably diminishes the expected number of steps to visit every state in the state space by a uniform random walk. We show empirically that the proposed algorithm improves the learning time in several domains with sparse rewards.

Dilip Arumugam, David Abel, Kavosh Asadi et al.

An agent with an inaccurate model of its environment faces a difficult choice: it can ignore the errors in its model and act in the real world in whatever way it determines is optimal with respect to its model. Alternatively, it can take a more conservative stance and eschew its model in favor of optimizing its behavior solely via real-world interaction. This latter approach can be exceedingly slow to learn from experience, while the former can lead to "planner overfitting" - aspects of the agent's behavior are optimized to exploit errors in its model. This paper explores an intermediate position in which the planner seeks to avoid overfitting through a kind of regularization of the plans it considers. We present three different approaches that demonstrably mitigate planner overfitting in reinforcement-learning environments.

Yuu Jinnai, David Abel, D Ellis Hershkowitz et al.

We formalize the problem of selecting the optimal set of options for planning as that of computing the smallest set of options so that planning converges in less than a given maximum of value-iteration passes. We first show that the problem is NP-hard, even if the task is constrained to be deterministic---the first such complexity result for option discovery. We then present the first polynomial-time boundedly suboptimal approximation algorithm for this setting, and empirically evaluate it against both the optimal options and a representative collection of heuristic approaches in simple grid-based domains including the classic four-rooms problem.

Christopher Grimm, Dilip Arumugam, Siddharth Karamcheti et al.

Deep neural networks are able to solve tasks across a variety of domains and modalities of data. Despite many empirical successes, we lack the ability to clearly understand and interpret the learned internal mechanisms that contribute to such effective behaviors or, more critically, failure modes. In this work, we present a general method for visualizing an arbitrary neural network's inner mechanisms and their power and limitations. Our dataset-centric method produces visualizations of how a trained network attends to components of its inputs. The computed "attention masks" support improved interpretability by highlighting which input attributes are critical in determining output. We demonstrate the effectiveness of our framework on a variety of deep neural network architectures in domains from computer vision, natural language processing, and reinforcement learning. The primary contribution of our approach is an interpretable visualization of attention that provides unique insights into the network's underlying decision-making process irrespective of the data modality.

David Abel, D. Ellis Hershkowitz, Michael L. Littman

The combinatorial explosion that plagues planning and reinforcement learning (RL) algorithms can be moderated using state abstraction. Prohibitively large task representations can be condensed such that essential information is preserved, and consequently, solutions are tractably computable. However, exact abstractions, which treat only fully-identical situations as equivalent, fail to present opportunities for abstraction in environments where no two situations are exactly alike. In this work, we investigate approximate state abstractions, which treat nearly-identical situations as equivalent. We present theoretical guarantees of the quality of behaviors derived from four types of approximate abstractions. Additionally, we empirically demonstrate that approximate abstractions lead to reduction in task complexity and bounded loss of optimality of behavior in a variety of environments.

David Abel, John Salvatier, Andreas Stuhlmüller et al.

Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to learn efficiently in complex environments; many of these methods tailor the teacher's guidance to agents with a particular representation or underlying learning scheme, offering effective but specialized teaching procedures. In this work, we explore protocol programs, an agent-agnostic schema for Human-in-the-Loop Reinforcement Learning. Our goal is to incorporate the beneficial properties of a human teacher into Reinforcement Learning without making strong assumptions about the inner workings of the agent. We show how to represent existing approaches such as action pruning, reward shaping, and training in simulation as special cases of our schema and conduct preliminary experiments on simple domains.

David Abel, Alekh Agarwal, Fernando Diaz et al.

High-dimensional observations and complex real-world dynamics present major challenges in reinforcement learning for both function approximation and exploration. We address both of these challenges with two complementary techniques: First, we develop a gradient-boosting style, non-parametric function approximator for learning on $Q$-function residuals. And second, we propose an exploration strategy inspired by the principles of state abstraction and information acquisition under uncertainty. We demonstrate the empirical effectiveness of these techniques, first, as a preliminary check, on two standard tasks (Blackjack and $n$-Chain), and then on two much larger and more realistic tasks with high-dimensional observation spaces. Specifically, we introduce two benchmarks built within the game Minecraft where the observations are pixel arrays of the agent's visual field. A combination of our two algorithmic techniques performs competitively on the standard reinforcement-learning tasks while consistently and substantially outperforming baselines on the two tasks with high-dimensional observation spaces. The new function approximator, exploration strategy, and evaluation benchmarks are each of independent interest in the pursuit of reinforcement-learning methods that scale to real-world domains.