arXiv subjects

Michael L. Littman

Publications and source records attributed to Michael L. Littman.

At least 19 recordsLinked to original sources

arXiv2026

Shared Lexical Task Representations Explain Behavioral Variability In LLMs

One of the most common complaints about large language models (LLMs) is their prompt sensitivity -- that is, the fact that their ability to perform a task or provide a correct answer to a question can depend unpredictably on the way the question is posed. We investigate this variation by comparing two very different but commonly-used styles of prompting: instruction-based prompts, which describe the task in natural language, and example-based prompts, which provide in-context few-shot demonstration pairs to illustrate the task. We find that, despite large variation in performance as a function of the prompt, the model engages some common underlying mechanisms across different prompts of a task. Specifically, we identify task-specific attention heads whose outputs literally describe the task -- which we dub lexical task heads -- and show that these heads are shared across prompting styles and trigger subsequent answer production. We further find that behavioral variation between prompts can be explained by the degree to which these heads are activated, and that failures are at least sometimes due to competing task representations that dilute the signal of the target task. Our results together present an increasingly clear picture of how LLMs' internal representations can explain behavior that otherwise seems idiosyncratic to users and developers.

cs.CL↗

arXiv2025

Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages

Recent works have explored using language models for planning problems. One approach examines translating natural language descriptions of planning tasks into structured planning languages, such as the planning domain definition language (PDDL). Existing evaluation methods struggle to ensure semantic correctness and rely on simple or unrealistic datasets. To bridge this gap, we introduce \textit{Planetarium}, a benchmark designed to evaluate language models' ability to generate PDDL code from natural language descriptions of planning tasks. \textit{Planetarium} features a novel PDDL equivalence algorithm that flexibly evaluates the correctness of generated PDDL, along with a dataset of 145,918 text-to-PDDL pairs across 73 unique state combinations with varying levels of difficulty. Finally, we evaluate several API-access and open-weight language models that reveal this task's complexity. For example, 96.1\% of the PDDL problem descriptions generated by GPT-4o are syntactically parseable, 94.4\% are solvable, but only 24.8\% are semantically correct, highlighting the need for a more rigorous benchmark for this problem.

cs.CL↗

arXiv2024

Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy

Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable, how can an agent learn such a state representation, and how can it detect when it has found one? We introduce a metric that can accomplish both objectives, without requiring access to -- or knowledge of -- an underlying, unobservable state space. Our metric, the $λ$-discrepancy, is the difference between two distinct temporal difference (TD) value estimates, each computed using TD($λ$) with a different value of $λ$. Since TD($λ{=}0$) makes an implicit Markov assumption and TD($λ{=}1$) does not, a discrepancy between these estimates is a potential indicator of a non-Markovian state representation. Indeed, we prove that the $λ$-discrepancy is exactly zero for all Markov decision processes and almost always non-zero for a broad class of partially observable environments. We also demonstrate empirically that, once detected, minimizing the $λ$-discrepancy can help with learning a memory function to mitigate the corresponding partial observability. We then train a reinforcement learning agent that simultaneously constructs two recurrent value networks with different $λ$ parameters and minimizes the difference between them as an auxiliary loss. The approach scales to challenging partially observable domains, where the resulting agent frequently performs significantly better (and never performs worse) than a baseline recurrent agent with only a single value network.

cs.LG↗

arXiv2024

Tiered Reward: Designing Rewards for Specification and Fast Learning of Desired Behavior

Reinforcement-learning agents seek to maximize a reward signal through environmental interactions. As humans, our job in the learning process is to design reward functions to express desired behavior and enable the agent to learn such behavior swiftly. However, designing good reward functions to induce the desired behavior is generally hard, let alone the question of which rewards make learning fast. In this work, we introduce a family of a reward structures we call Tiered Reward that addresses both of these questions. We consider the reward-design problem in tasks formulated as reaching desirable states and avoiding undesirable states. To start, we propose a strict partial ordering of the policy space to resolve trade-offs in behavior preference. We prefer policies that reach the good states faster and with higher probability while avoiding the bad states longer. Next, we introduce Tiered Reward, a class of environment-independent reward functions and show it is guaranteed to induce policies that are Pareto-optimal according to our preference relation. Finally, we demonstrate that Tiered Reward leads to fast learning with multiple tabular and deep reinforcement-learning algorithms.

cs.LG↗

arXiv2023

Faster Deep Reinforcement Learning with Slower Online Network

Deep reinforcement learning algorithms often use two networks for value function optimization: an online network, and a target network that tracks the online network with some delay. Using two separate networks enables the agent to hedge against issues that arise when performing bootstrapping. In this paper we endow two popular deep reinforcement learning algorithms, namely DQN and Rainbow, with updates that incentivize the online network to remain in the proximity of the target network. This improves the robustness of deep reinforcement learning in presence of noisy updates. The resultant agents, called DQN Pro and Rainbow Pro, exhibit significant performance improvements over their original counterparts on the Atari benchmark demonstrating the effectiveness of this simple idea in deep reinforcement learning. The code for our paper is available here: Github.com/amazon-research/fast-rl-with-slow-updates.

cs.LG↗

arXiv2023

Interactive Learning from Policy-Dependent Human Feedback

This paper investigates the problem of interactively learning behaviors communicated by a human teacher using positive and negative feedback. Much previous work on this problem has made the assumption that people provide feedback for decisions that is dependent on the behavior they are teaching and is independent from the learner's current policy. We present empirical results that show this assumption to be false -- whether human trainers give a positive or negative feedback for a decision is influenced by the learner's current policy. Based on this insight, we introduce {\em Convergent Actor-Critic by Humans} (COACH), an algorithm for learning from policy-dependent feedback that converges to a local optimum. Finally, we demonstrate that COACH can successfully learn multiple behaviors on a physical robot.

cs.AI↗

arXiv2023

A Domain-Agnostic Approach for Characterization of Lifelong Learning Systems

Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the original training context, and systems will instead need to adapt to novel distributions and tasks while deployed. This critical gap may be addressed through the development of "Lifelong Learning" systems that are capable of 1) Continuous Learning, 2) Transfer and Adaptation, and 3) Scalability. Unfortunately, efforts to improve these capabilities are typically treated as distinct areas of research that are assessed independently, without regard to the impact of each separate capability on other aspects of the system. We instead propose a holistic approach, using a suite of metrics and an evaluation framework to assess Lifelong Learning in a principled way that is agnostic to specific domains or system techniques. Through five case studies, we show that this suite of metrics can inform the development of varied and complex Lifelong Learning systems. We highlight how the proposed suite of metrics quantifies performance trade-offs present during Lifelong Learning system development - both the widely discussed Stability-Plasticity dilemma and the newly proposed relationship between Sample Efficient and Robust Learning. Further, we make recommendations for the formulation and use of metrics to guide the continuing development of Lifelong Learning systems and assess their progress in the future.

cs.LG↗

arXiv2022

Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex

AlphaZero, an approach to reinforcement learning that couples neural networks and Monte Carlo tree search (MCTS), has produced state-of-the-art strategies for traditional board games like chess, Go, shogi, and Hex. While researchers and game commentators have suggested that AlphaZero uses concepts that humans consider important, it is unclear how these concepts are captured in the network. We investigate AlphaZero's internal representations in the game of Hex using two evaluation techniques from natural language processing (NLP): model probing and behavioral tests. In doing so, we introduce new evaluation tools to the RL community and illustrate how evaluations other than task performance can be used to provide a more complete picture of a model's strengths and weaknesses. Our analyses in the game of Hex reveal interesting patterns and generate some testable hypotheses about how such models learn in general. For example, we find that MCTS discovers concepts before the neural network learns to encode them. We also find that concepts related to short-term end-game planning are best encoded in the final layers of the model, whereas concepts related to long-term planning are encoded in the middle layers of the model.

cs.AI↗

arXiv2022

People construct simplified mental representations to plan

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.

cs.AI↗

arXiv2022

Reward-Predictive Clustering

Recent advances in reinforcement-learning research have demonstrated impressive results in building algorithms that can out-perform humans in complex tasks. Nevertheless, creating reinforcement-learning systems that can build abstractions of their experience to accelerate learning in new contexts still remains an active area of research. Previous work showed that reward-predictive state abstractions fulfill this goal, but have only be applied to tabular settings. Here, we provide a clustering algorithm that enables the application of such state abstractions to deep learning settings, providing compressed representations of an agent's inputs that preserve the ability to predict sequences of reward. A convergence theorem and simulations show that the resulting reward-predictive deep network maximally compresses the agent's inputs, significantly speeding up learning in high dimensional visual control tasks. Furthermore, we present different generalization experiments and analyze under which conditions a pre-trained reward-predictive representation network can be re-used without re-training to accelerate learning -- a form of systematic out-of-distribution transfer.

cs.LG↗

arXiv2022

Gathering Strength, Gathering Storms: The One Hundred Year Study on Artificial Intelligence (AI100) 2021 Study Panel Report

In September 2021, the "One Hundred Year Study on Artificial Intelligence" project (AI100) issued the second report of its planned long-term periodic assessment of artificial intelligence (AI) and its impact on society. It was written by a panel of 17 study authors, each of whom is deeply rooted in AI research, chaired by Michael Littman of Brown University. The report, entitled "Gathering Strength, Gathering Storms," answers a set of 14 questions probing critical areas of AI development addressing the major risks and dangers of AI, its effects on society, its public perception and the future of the field. The report concludes that AI has made a major leap from the lab to people's lives in recent years, which increases the urgency to understand its potential negative effects. The questions were developed by the AI100 Standing Committee, chaired by Peter Stone of the University of Texas at Austin, consisting of a group of AI leaders with expertise in computer science, sociology, ethics, economics, and other disciplines.

cs.AI↗

arXiv2022

Designing Rewards for Fast Learning

To convey desired behavior to a Reinforcement Learning (RL) agent, a designer must choose a reward function for the environment, arguably the most important knob designers have in interacting with RL agents. Although many reward functions induce the same optimal behavior (Ng et al., 1999), in practice, some of them result in faster learning than others. In this paper, we look at how reward-design choices impact learning speed and seek to identify principles of good reward design that quickly induce target behavior. This reward-identification problem is framed as an optimization problem: Firstly, we advocate choosing state-based rewards that maximize the action gap, making optimal actions easy to distinguish from suboptimal ones. Secondly, we propose minimizing a measure of the horizon, something we call the "subjective discount", over which rewards need to be optimized to encourage agents to make optimal decisions with less lookahead. To solve this optimization problem, we propose a linear-programming based algorithm that efficiently finds a reward function that maximizes action gap and minimizes subjective discount. We test the rewards generated with the algorithm in tabular environments with Q-Learning, and empirically show they lead to faster learning. Although we only focus on Q-Learning because it is perhaps the simplest and most well understood RL algorithm, preliminary results with R-max (Brafman and Tennenholtz, 2000) suggest our results are much more general. Our experiments support three principles of reward design: 1) consistent with existing results, penalizing each step taken induces faster learning than rewarding the goal. 2) When rewarding subgoals along the target trajectory, rewards should gradually increase as the goal gets closer. 3) Dense reward that's nonzero on every state is only good if designed carefully.

cs.LG↗

arXiv2022

On the Expressivity of Markov Reward

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.

cs.LG↗

arXiv2021

Towards Sample Efficient Agents through Algorithmic Alignment

In this work, we propose and explore Deep Graph Value Network (DeepGV) as a promising method to work around sample complexity in deep reinforcement-learning agents using a message-passing mechanism. The main idea is that the agent should be guided by structured non-neural-network algorithms like dynamic programming. According to recent advances in algorithmic alignment, neural networks with structured computation procedures can be trained efficiently. We demonstrate the potential of graph neural network in supporting sample efficient learning by showing that Deep Graph Value Network can outperform unstructured baselines by a large margin in solving the Markov Decision Process (MDP). We believe this would open up a new avenue for structured agent design. See https://github.com/drmeerkat/Deep-Graph-Value-Network for the code.

cs.AI↗

arXiv2021

Bad-Policy Density: A Measure of Reinforcement Learning Hardness

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.

cs.LG↗

arXiv2021

Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback

Fluid human-agent communication is essential for the future of human-in-the-loop reinforcement learning. An agent must respond appropriately to feedback from its human trainer even before they have significant experience working together. Therefore, it is important that learning agents respond well to various feedback schemes human trainers are likely to provide. This work analyzes the COnvergent Actor-Critic by Humans (COACH) algorithm under three different types of feedback-policy feedback, reward feedback, and advantage feedback. For these three feedback types, we find that COACH can behave sub-optimally. We propose a variant of COACH, episodic COACH (E-COACH), which we prove converges for all three types. We compare our COACH variant with two other reinforcement-learning algorithms: Q-learning and TAMER.

cs.LG↗

arXiv2021

Brittle AI, Causal Confusion, and Bad Mental Models: Challenges and Successes in the XAI Program

The advances in artificial intelligence enabled by deep learning architectures are undeniable. In several cases, deep neural network driven models have surpassed human level performance in benchmark autonomy tasks. The underlying policies for these agents, however, are not easily interpretable. In fact, given their underlying deep models, it is impossible to directly understand the mapping from observations to actions for any reasonably complex agent. Producing this supporting technology to "open the black box" of these AI systems, while not sacrificing performance, was the fundamental goal of the DARPA XAI program. In our journey through this program, we have several "big picture" takeaways: 1) Explanations need to be highly tailored to their scenario; 2) many seemingly high performing RL agents are extremely brittle and are not amendable to explanation; 3) causal models allow for rich explanations, but how to present them isn't always straightforward; and 4) human subjects conjure fantastically wrong mental models for AIs, and these models are often hard to break. This paper discusses the origins of these takeaways, provides amplifying information, and suggestions for future work.

cs.AI↗

arXiv2021

Lipschitz Lifelong Reinforcement Learning

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.

cs.LG↗