91 accepted papers
A hallmark of intelligence is the ability to adapt in non-stationary environments, yet deep Reinforcement Learning (RL) agents often struggle in such settings. Most prior studies introduce non-stationarity through abrupt shifts in features or dynamics, whereas real-world changes might be more gradua…
Personalized insulin therapy for individuals with Type 1 Diabetes via closed‑loop artificial pancreas systems requires rapid adaptation of dosing strategies to each patient
We find multilayer perceptrons and transformers both universally learn an instantiation of the same divide-and-conquer algorithm that requires only a logarithmic number of neural representations to solve dihedral multiplication. Clustering neurons based on similar activation behaviour reveals remark…
Agents that can beat or tie any other under a model of pairwise preference have strong guarantees for both user satisfaction and overall social welfare. However, searching for these agents in long-term decision problems is not computationally tractable with current approaches, which require the size…
Reward models (RMs) are fundamental to aligning Large Language Models (LLMs) via human feedback, yet they often suffer from reward hacking. They tend to latch on to superficial or spurious attributes, such as response length or formatting, mistaking these cues learned from correlations in training d…
The Clock and Pizza interpretations, associated with architectures differing in either uniform or learnable attention, were introduced to argue that different architectural designs can yield distinct circuits for modular addition. In this work, we show that this is not the case, and that both the un…
Reinforcement learning from human feedback usually models preferences using a reward function that does not distinguish between people. We argue that this is unlikely to be a good design choice in contexts with high potential for disagreement, like in the training of large language models. We formal…
Existing actor-critic algorithms, which are popular for continuous control reinforcement learning (RL) tasks, suffer from poor sample efficiency due to lack of principled exploration mechanism within them. Motivated by the success of Thompson sampling for efficient exploration in RL, we propose a no…
Describing skills in natural language has the potential to provide an accessible way to inject human knowledge about decision-making into an AI system. We present MaestroMotif, a method for AI-assisted skill design, which yields high-performing and adaptable agents. MaestroMotif leverages the capabi…
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…
Generative models can be used in planning to propose targets corresponding to states that agents deem either likely or advantageous to experience. However, imperfections, common in learned models, lead to infeasible hallucinated targets, which can cause delusional behaviors and thus safety concerns.…
When deploying machine learning models in the real world, we often face the challenge of “unlearning” specific data points or subsets after training. Inspired by Domain-Adversarial Training of Neural Networks (DANN), we propose a novel algorithm,SURE, for targeted unlearning.SURE treats the proces…
Self-correction is a highly desirable capability of large language models (LLMs), yet it has consistently been found to be largely ineffective in modern LLMs. Current methods for training self-correction typically depend on either multiple models, a more advanced model, or additional forms of super…
We propose a testable universality hypothesis, asserting that seemingly disparate neural network solutions observed in the simple task of modular addition actually reflect a common abstract algorithm. While prior work interpreted variations in neuron-level representations as evidence for distinct al…
General Value Functions (GVFs) (Sutton et al., 2011) represent predictive knowledge in reinforcement learning. Each GVF computes the expected return for a given policy, based on a unique reward. Existing methods relying on fixed behavior policies or pre-collected data often face data efficiency issu…
Pre-trained Vision-Language Models (VLMs) are able to understand visual concepts, describe and decompose complex tasks into sub-tasks, and provide feedback on task completion. In this paper, we aim to leverage these capabilities to support the training of reinforcement learning (RL) agents. In princ…
Learning from Preferential Feedback (LfPF) plays an essential role in training Large Language Models, as well as certain types of interactive learning agents. However, a substantial gap exists between the theory and application of LfPF algorithms. Current results guaranteeing the existence of optima…
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 decisio…
This paper describes the Ubenwa CryCeleb dataset - a labeled collection of infant cries - and the accompanying CryCeleb 2023 task, which is a public speaker verification challenge based on cry sounds. We released more than 6 hours of manually segmented cry sounds from 786 newborns for academic use,…
We consider the problem of sampling from a discrete and structured distribution as a sequential decision problem, where the objective is to find a stochastic policy such that objects are sampled at the end of this sequential process proportionally to some predefined reward. While we could use maximu…
Reinforcement learning (RL) algorithms have been very successful at tackling complex control problems, such as AlphaGo or fusion control. However, current research mainly emphasizes solution quality, often achieved by using large models trained on large amounts of data, and does not account for the…
This work proposes a new learning-to-search benchmark and uses AI to discover new mathematical knowledge related to an open conjecture of Erdos (1975) in extremal graph theory. The problem is to find graphs with a given size (number of nodes) that maximize the number of edges without having 3- or 4-…
In Deep Reinforcement Learning (RL), it is a challenge to learn representations that do not exhibit catastrophic forgetting or interference in non-stationary environments. Successor Features (SFs) offer a potential solution to this challenge. However, canonical techniques for learning SFs from pixel…
The recent rapid progress in (self) supervised learning models is in large part predicted by empirical scaling laws: a model's performance scales proportionally to its size. Analogous scaling laws remain elusive for reinforcement learning domains, however, where increasing the parameter count of a m…
Reinforcement learning from human feedback (RLHF) has emerged as the main paradigm for aligning large language models (LLMs) with human preferences. Traditionally, RLHF involves the initial step of learning a reward model from pairwise human feedback, i.e., expressed as preferences between pairs of…
We study offline multitask representation learning in reinforcement learning (RL), where a learner is provided with an offline dataset from different tasks that share a common representation and is asked to learn the shared representation. We theoretically investigate offline multitask low-rank RL,…
Reinforcement learning (RL) folklore suggests that methods of function approximation based on history, such as recurrent neural networks or state abstractions that include past information, outperform those without memory, because function approximation in Markov decision processes (MDP) can lead to…
Report Noisy Max and Above Threshold are two classical differentially private (DP) selection mechanisms. Their output is obtained by adding noise to a sequence of low-sensitivity queries and reporting the identity of the query whose (noisy) answer satisfies a certain condition. Pure DP guarantees fo…
Plasticity loss, trainability loss, and primacy bias have been identified as issues arising when training deep neural networks on sequences of tasks---referring to the increased difficulty in training on new tasks. We propose to use Parseval regularization, which maintains orthogonality of weight ma…
We present a scalable and effective exploration strategy based on Thompson sampling for reinforcement learning (RL). One of the key shortcomings of existing Thompson sampling algorithms is the need to perform a Gaussian approximation of the posterior distribution, which is not a good surrogate in m…
Generative Flow Networks (GFlowNets; GFNs) are a family of energy-based generative methods for combinatorial objects, capable of generating diverse and high-utility samples. However, consistently biasing GFNs towards producing high-utility samples is non-trivial. In this work, we leverage connection…
Enzymes, with their specific catalyzed reactions, are necessary for all aspects of life, enabling diverse biological processes and adaptations. Predicting enzyme functions is essential for understanding biological pathways, guiding drug development, enhancing bioproduct yields, and facilitating evol…
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,…
We study the finite-time behaviour of the popular temporal difference (TD) learning algorithm, when combined with tail-averaging. We derive finite time bounds on the parameter error of the tail-averaged TD iterate under a step-size choice that does not require information about the eigenvalues of th…
In reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked for environments with low-level states, such as physical control problems. This paper introduces SALE, a novel approach for learning embeddings that model the nuanced inte…
Using massive datasets to train large-scale models has emerged as a dominant approach for broad generalization in natural language and vision applications. In reinforcement learning, however, a key challenge is that available data of sequential decision making is often not annotated with actions - f…
Drug dosing is an important application of AI, which can be formulated as a Reinforcement Learning (RL) problem. In this paper, we identify two major challenges of using RL for drug dosing: delayed and prolonged effects of administering medications, which break the Markov assumption of the RL framew…
Temporal difference (TD) learning is often used to update the estimate of the value function which is used by RL agents to extract useful policies. In this paper, we focus on value function estimation in continual reinforcement learning. We propose to decompose the value function into two components…
Mechanical ventilation is a key form of life support for patients with pulmonary impairment. Healthcare workers are required to continuously adjust ventilator settings for each patient, a challenging and time consuming task. Hence, it would be beneficial to develop an automated decision support tool…
Homophily principle, i.e., nodes with the same labels are more likely to be connected, has been believed to be the main reason for the performance superiority of Graph Neural Networks (GNNs) over Neural Networks on node classification tasks. Recent research suggests that, even in the absence of homo…
We consider the offline constrained reinforcement learning (RL) problem, in which the agent aims to compute a policy that maximizes expected return while satisfying given cost constraints, learning only from a pre-collected dataset. This problem setting is appealing in many real-world scenarios, whe…
We study the problem of learning a good set of policies, so that when combined together, they can solve a wide variety of unseen reinforcement learning tasks with no or very little new data. Specifically, we consider the framework of generalized policy evaluation and improvement, in which the reward…
Abstraction has been widely studied as a way to improve the efficiency and generalization of reinforcement learning algorithms. In this paper, we study abstraction in the continuous-control setting. We extend the definition of MDP homomorphisms to encompass continuous actions in continuous state spa…
The reliability of neural networks is essential for their use in safety-critical applications. Existing approaches generally aim at improving the robustness of neural networks to either real-world distribution shifts (e.g., common corruptions and perturbations, spatial transformations, and natural a…
Reward is the driving force for reinforcement-learning agents. We here set out to understand the expressivity of Markov 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": (1) a set of acceptable behaviors…
Reasoning about the future -- understanding how decisions in the present time affect outcomes in the future -- is one of the central challenges for reinforcement learning (RL), especially in highly-stochastic or partially observable environments. While predicting the future directly is hard, in this…
Traditional automated theorem proving systems for first-order logic depend on speed-optimized search and many handcrafted heuristics designed to work over a wide range of domains. Machine learning approaches in the literature either depend on these traditional provers to bootstrap themselves, by lev…
Graph Neural Networks (GNNs) extend basic Neural Networks (NNs) by using graph structures based on the relational inductive bias (homophily assumption). While GNNs have been commonly believed to outperform NNs in real-world tasks, recent work has identified a non-trivial set of datasets where their…
We study policy optimization in an infinite horizon, $\gamma$-discounted constrained Markov decision process (CMDP). Our objective is to return a policy that achieves large expected reward with a small constraint violation. We consider the online setting with linear function approximation and assume…
In this work, we study the use of the Bellman equation as a surrogate objective for value prediction accuracy. While the Bellman equation is uniquely solved by the true value function over all state-action pairs, we find that the Bellman error (the difference between both sides of the equation) is a…
We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning. The agent uses a bottleneck mechanism over a set-based representation to force the number of entities to which the agent attends at each planning step to…
Marginalized importance sampling (MIS), which measures the density ratio between the state-action occupancy of a target policy and that of a sampling distribution, is a promising approach for off-policy evaluation. However, current state-of-the-art MIS methods rely on complex optimization tricks and…
Temporal abstraction in reinforcement learning (RL), offers the promise of improving generalization and knowledge transfer in complex environments, by propagating information more efficiently over time. Although option learning was initially formulated in a way that allows updating many options simu…
This paper is about the problem of learning a stochastic policy for generating an object (like a molecular graph) from a sequence of actions, such that the probability of generating an object is proportional to a given positive reward for that object. Whereas standard return maximization tends to co…
We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of features relevant for the task, despite the presence of other pr…
A major challenge in reinforcement learning is the design of exploration strategies, especially for environments with sparse reward structures and continuous state and action spaces. Intuitively, if the reinforcement signal is very scarce, the agent should rely on some form of short-term memory in o…
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 a…
Temporal-Difference (TD) learning is a general and very useful tool for estimating the value function of a given policy, which in turn is required to find good policies. Generally speaking, TD learning updates states whenever they are visited. When the agent lands in a state, its value can be used t…
We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm as well as the optimism principle. Unlike existing upper-confidence-bound (UCB) based approaches, which are often computationally intractable, our algorithm dri…
Visual saliency has emerged as a major visualization tool for interpreting deep reinforcement learning (RL) agents. However, much of the existing research uses it as an analyzing tool rather than an inductive bias for policy learning. In this work, we use visual attention as an inductive bias for RL…
Humans and animals have the ability to reason and make predictions about different courses of action at many time scales. In reinforcement learning, option models (Sutton, Precup \& Singh, 1999; Precup, 2000) provide the framework for this kind of temporally abstract prediction and reasoning. Natura…
Reinforcement learning algorithms are typically geared towards optimizing the expected return of an agent. However, in many practical applications, low variance in the return is desired to ensure the reliability of an algorithm. In this paper, we propose on-policy and off-policy actor-critic algorit…
We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a variety of commonly-used methods. We show that value-based methods such as TD(?) an…
Prioritized Experience Replay (PER) is a deep reinforcement learning technique in which agents learn from transitions sampled with non-uniform probability proportionate to their temporal-difference error. We show that any loss function evaluated with non-uniformly sampled data can be transformed int…
Learning and planning in partially-observable domains is one of the most difficult problems in reinforcement learning. Traditional methods consider these two problems as independent, resulting in a classic two-stage paradigm: first learn the environment dynamics and then compute the optimal policy a…
We address the problem of credit assignment in reinforcement learning and explore fundamental questions regarding the way in which an agent can best use additional computation to propagate new information, by planning with internal models of the world to improve its predictions. Particularly, we wor…
We study the link between generalization and interference in temporal-difference (TD) learning. Interference is defined as the inner product of two different gradients, representing their alignment; this quantity emerges as being of interest from a variety of observations about neural networks, para…
Generalization across environments is critical to the successful application of reinforcement learning (RL) algorithms to real-world challenges. In this work we propose a method for learning state abstractions which generalize to novel observation distributions in the multi-environment RL setting. W…
Hierarchical Reinforcement Learning (HRL) approaches promise to provide more efficient solutions to sequential decision making problems, both in terms of statistical as well as computational efficiency. While this has been demonstrated empirically over time in a variety of tasks, theoretical results…
Potential-based reward shaping provides an approach for designing good reward functions, with the purpose of speeding up learning. However, automatically finding potential functions for complex environments is a difficult problem (in fact, of the same difficulty as learning a value function from scr…
Stochastic variance-reduced gradient (SVRG) is an optimization method originally designed for tackling machine learning problems with a finite sum structure. SVRG was later shown to work for policy evaluation, a problem in reinforcement learning in which one aims to estimate the value function of a…
Abstraction can improve the sample efficiency of reinforcement learning. However, the process of abstraction inherently discards information, potentially compromising an agent’s ability to represent high-value policies. To mitigate this, we here introduce combinations of state abstractions and optio…
Value estimation is a critical component of the reinforcement learning (RL) paradigm. The question of how to effectively learn value predictors from data is one of the major problems studied by the RL community, and different approaches exploit structure in the problem domain in different ways. Mod…
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 fa…
Recently, neural network based approaches have achieved significant progress for solving large, complex, graph-structured problems. Nevertheless, the advantages of multi-scale information and deep architectures have not been sufficiently exploited. In this paper, we first analyze key factors constra…
In this paper, we unravel a fundamental connection between weighted finite automata (WFAs) and second-order recurrent neural networks (2-RNNs): in the case of sequences of discrete symbols, WFAs and 2-RNNs with linear activation functions are expressively equivalent. Motivated by this result, we bui…
We consider the problem of efficient credit assignment in reinforcement learning. In order to efficiently and meaningfully utilize new data, we propose to explicitly assign credit to past decisions based on the likelihood of them having led to the observed outcome. This approach uses new information…
Millions of blind and visually-impaired (BVI) people navigate urban environments everyday, using smartphones for high-level path-planning and white canes or guide dogs for local information. However, many BVI people still struggle to travel to new places. In our endeavour to create a navigation assi
Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to errors introduced by extrapolation, standard off-policy deep…
In order to solve complex problems an agent must be able to reason over a sufficiently long horizon. Temporal abstraction, commonly modeled through options, offers the ability to reason at many timescales, but the horizon length is still determined by the discount factor of the underlying Markov Dec…
The ability to combine known skills to create new ones may be crucial in the solution of complex reinforcement learning problems that unfold over extended periods. We argue that a robust way of combining skills is to define and manipulate them in the space of pseudo-rewards (or "cumulants"). Based o…
In this work, we consider the problem of autonomously discovering behavioral abstractions, or options, for reinforcement learning agents. We propose an algorithm that focuses on the termination function, as opposed to - as is common - the policy. The termination function is usually trained to optim…
Diversity of environments is a key challenge that causes learned robotic controllers to fail due to the discrepancies between the training and evaluation conditions. Training from demonstrations in various conditions can mitigate - but not completely prevent - such failures. Learned controllers such…
Off-policy learning is key to scaling up reinforcement learning as it allows to learn about a target policy from the experience generated by a different behavior policy. Unfortunately, it has been challenging to combine off-policy learning with function approximation and multi-step bootstrapping in…
We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existence of demonstrations from expert policies, and we provide a theoretical framework for the agent to optimize in the spac…
Weighted finite automata (WFA) can expressively model functions defined over strings but are inherently linear models.Given the recent successes of non-linear models in machine learning, it is natural to wonder whether extending WFA to the non-linearsetting would be beneficial.In this paper, we prop…
Several applications of Reinforcement Learning suffer from instability due to high variance. This is especially prevalent in high dimensional domains. Regularization is a commonly used technique in machine learning to reduce variance, at the cost of introducing some bias. Most existing regularizatio…
We present the first differentially private algorithms for reinforcement learning, which apply to the task of evaluating a fixed policy. We establish two approaches for achieving differential privacy, provide a theoretical analysis of the privacy and utility of the two algorithms, and show promising…
We provide a theoretical framework for analyzing basis function construction for linear value function approximation in Markov Decision Processes (MDPs). We show that important existing methods, such as Krylov bases and Bellman-error-based methods are a special case of the general framework we devel…
We connect a broad class of generative models through their shared reliance on sequential decision making. Motivated by this view, we develop extensions to an existing model, and then explore the idea further in the context of data imputation -- perhaps the simplest setting in which to investigate t…
We develop an approach to training generative models based on unrolling a variational auto-encoder into a Markov chain, and shaping the chain’s trajectories using a technique inspired by recent work in Approximate Bayesian computation. We show that the global minimizer of the resulting objective is…