50 accepted papers
Behavioral Foundation Models (BFMs) have been recently successful in producing agents with the capabilities to adapt to any unknown reward or task. In reality, these methods are only able to produce near-optimal policies for the reward functions that are in the span of some pre-existing _state featu…
We introduce Iterative Dual Reinforcement Learning (IDRL), a new method that takes an optimal discriminator-weighted imitation view of solving RL. Our method is motivated by a simple experiment in which we find training a discriminator using the offline dataset plus an additional expert dataset and…
Hindsight relabeling is a powerful tool for overcoming sparsity in goal-conditioned reinforcement learning (GCRL), especially in certain domains such as navigation and locomotion. However, hindsight relabeling can struggle in object-centric domains. For example, suppose that the goal space consists…
The reward hypothesis states that all goals and purposes can be understood as the maximization of a received scalar reward signal. However, in practice, defining such a reward signal is notoriously difficult, as humans are often unable to predict the optimal behavior corresponding to a reward func…
Demonstrations are an effective alternative to task specification for learning agents in settings where designing a reward function is difficult. However, demonstrating expert behavior in the action space of the agent becomes unwieldy when robots have complex, unintuitive morphologies. We consider t…
Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for aligning models with human intent. Typically RLHF algorithms operate in two phases: first, use human preferences to learn a reward function and second, align the model by optimizing the learned reward via reinfor…
The goal of reinforcement learning (RL) is to find a policy that maximizes the expected cumulative return. It has been shown that this objective can be represented as an optimization problem of state-action visitation distribution under linear constraints. The dual problem of this formulation, which…
We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work assumes that human preferences are generated based only upon the reward accrued within those segments, or thei…
As reinforcement learning agents become increasingly deployed in real-world scenarios, predicting future agent actions and events during deployment is important for facilitating better human-agent interaction and preventing catastrophic outcomes. This paper experimentally evaluates and compares the…
Reinforcement Learning from Human Feedback (RLHF)has been crucial to the recent success of Large Language Models (LLMs), however it is often a complex and brittle process. In the classical RLHF framework, a reward model is first trained to represent human preferences, which is in turn used by an onl…
Offline Goal-Conditioned Reinforcement Learning (GCRL) is tasked with learning to achieve multiple goals in an environment purely from offline datasets using sparse reward functions. Offline GCRL is pivotal for developing generalist agents capable of leveraging pre-existing datasets to learn diverse…
Unsupervised skill discovery carries the promise that an intelligent agent can learn reusable skills through autonomous, reward-free interactions with environments. Existing unsupervised skill discovery methods learn skills by encouraging distinguishable behaviors that cover diverse states. However,…
In reinforcement learning (RL), a reward function that aligns exactly with a task's true performance metric is often necessarily sparse. For example, a true task metric might encode a reward of 1 upon success and 0 otherwise. The sparsity of these true task metrics can make them hard to learn from,…
Recent studies have demonstrated that using machine learning for social applications can lead to injustice in the form of racist, sexist, and otherwise unfair and discriminatory outcomes. To address this challenge, recent machine learning algorithms have been designed to limit the likelihood such un…
Humans use audio signals in the form of spoken language or verbal reactions effectively when teaching new skills or tasks to other humans. While demonstrations allow humans to teach robots in a natural way, learning from trajectories alone does not leverage other available modalities including audio…
Learning with an objective to minimize the mismatch with a reference distribution has been shown to be useful for generative modeling and imitation learning. In this paper, we investigate whether one such objective, the Wasserstein-1 distance between a policy's state visitation distribution and a ta…
We propose a method that efficiently learns distributions over articulation models directly from depth images without the need to know articulation model categories a priori. By contrast, existing methods that learn articulation models from raw observations require objects to be textured, and most o…
We introduce a sample-efficient method for learning state-dependent stiffness control policies for dexterous manipulation. The ability to control stiffness facilitates safe and reliable manipulation by providing compliance and robustness to uncertainties. Most current reinforcement learning approach…
Many sequential decision making problems are high-stakes and require off-policy evaluation (OPE) of a new policy using historical data collected using some other policy. One of the most common OPE techniques that provides unbiased estimates is trajectory based importance sampling (IS). However, due…
Robots in human environments will need to interact with a wide variety of articulated objects such as cabinets, drawers, and dishwashers while assisting humans in performing day-to-day tasks. Existing methods either require objects to be textured or need to know the articulation model category a pri…
We introduce Self-supervised Online Reward Shaping (SORS), which aims to improve the sample efficiency of any RL algorithm in sparse-reward environments by automatically densifying rewards. The proposed framework alternates between classification-based reward inference and policy update steps—the or…
Human-in-the-loop Machine Learning (HIL-ML) is a widely adopted paradigm for instilling human knowledge in autonomous agents. Many design choices influence the efficiency and effectiveness of such interactive learning processes, particularly the interaction type through which the human teacher may p…
When faced with sequential decision-making problems, it is often useful to be able to predict what would happen if decisions were made using a new policy. Those predictions must often be based on data collected under some previously used decision-making rule. Many previous methods enable such off-p…
As humans interact with autonomous agents to perform increasingly complicated, potentially risky tasks, it is important to be able to efficiently evaluate an agent’s performance and correctness. In this paper we formalize and theoretically analyze the problem of efficient value alignment verificatio…
The goal of offline reinforcement learning (RL) is to find an optimal policy given prerecorded trajectories. Many current approaches customize existing off-policy RL algorithms, especially actor-critic algorithms in which policy evaluation and improvement are iterated. However, the convergence of su…
One of the main challenges in imitation learning is determining what action an agent should take when outside the state distribution of the demonstrations. Inverse reinforcement learning (IRL) can enable generalization to new states by learning a parameterized reward function, but these approaches s…
Human gaze reveals a wealth of information about internal cognitive state. Thus, gaze-related research has significantly increased in computer vision, natural language processing, decision learning, and robotics in recent years. We provide a high-level overview of the research efforts in these field…
Deep reinforcement learning (DRL) is capable of learning high-performing policies on a variety of complex high-dimensional tasks, ranging from video games to robotic manipulation. However, standard DRL methods often suffer from poor sample efficiency, partially because they aim to be entirely proble…
Sudden changes in the dynamics of robotic tasks, such as contact with an object or the latching of a door, are often viewed as inconvenient discontinuities that make manipulation difficult. However, when these transitions are well-understood, they can be leveraged to reduce uncertainty or aid manipu…
Reinforcement learning (RL), particularly in sparse reward settings, often requires prohibitively large numbers of interactions with the environment, thereby limiting its applicability to complex problems. To address this, several prior approaches have used natural language to guide the agent’s expl
Bayesian reward learning from demonstrations enables rigorous safety and uncertainty analysis when performing imitation learning. However, Bayesian reward learning methods are typically computationally intractable for complex control problems. We propose Bayesian Reward Extrapolation (Bayesian REX),…
Reactions such as gestures, facial expressions, and vocalizations are an abundant, naturally occurring channel of information that humans provide during interactions. A robot or other agent could leverage an understanding of such implicit human feedback to improve its task performance at no cost to
The performance of imitation learning is typically upper-bounded by the performance of the demonstrator. While recent empirical results demonstrate that ranked demonstrations allow for better-than-demonstrator performance, preferences over demonstrations may be difficult to obtain, and little is kno
A critical flaw of existing inverse reinforcement learning (IRL) methods is their inability to significantly outperform the demonstrator. This is because IRL typically seeks a reward function that makes the demonstrator appear near-optimal, rather than inferring the underlying intentions of the demo…
We consider the problem of off-policy evaluation in Markov decision processes. Off-policy evaluation is the task of evaluating the expected return of one policy with data generated by a different, behavior policy. Importance sampling is a technique for off-policy evaluation that re-weights off-polic…
Due to burdensome data requirements, learning from demonstration often falls short of its promise to allow users to quickly and naturally program robots. Demonstrations are inherently ambiguous and incomplete, making correct generalization to unseen situations difficult without a large number of dem…
Estimating statistical uncertainties allows autonomous agents to communicate their confidence during task execution and is important for applications in safety-critical domains such as autonomous driving. In this work, we present the uncertainty-aware imitation learning (UAIL) algorithm for improvin…
Human gaze is known to be a strong indicator of underlying human intentions and goals during manipulation tasks. This work studies gaze patterns of human teachers demonstrating tasks to robots and proposes ways in which such patterns can be used to enhance robot learning. Using both kinesthetic teac
Learning from demonstration algorithms, such as Inverse Reinforcement Learning, aim to provide a natural mechanism for programming robots, but can often require a prohibitive number of demonstrations to capture important subtleties of a task. Rather than requesting additional demonstrations blindly,…
Noisy observations coupled with nonlinear dynamics pose one of the biggestchallengesinrobotmotionplanning. Bydecomposingnonlineardynamics into a discrete set of local dynamics models, hybrid dynamics provide a natural way to model nonlinear dynamics, especially in systems with sudden discontinuities
Gaze provides subtle informative cues to aid fluent interactions among people. Incorporating human gaze predictions can signify how engaged a person is while interacting with a robot and allow the robot to predict a human's intentions or goals. We propose a novel approach to predict human gaze fixat…
In realistic environments, fully specifying a task model such that a robot can perform a task in all situations is impractical. In this work, we present Incremental Task Modification via Corrective Demonstrations (ITMCD), a novel algorithm that allows a robot to update a learned model by making use…
Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the
Classification techniques are useful for processing complex signals into labels with semantic value. For example, they can be used to interpret brain signals generated by humans corresponding to a finite set of commands for a physical device. The classifier, however, may interpret the signal as a co…
We consider the task of evaluating a policy for a Markov decision process (MDP). The standard unbiased technique for evaluating a policy is to deploy the policy and observe its performance. We show that the data collected from deploying a different policy, commonly called the behavior policy, can be…
The visual difference between outcomes in many robotics tasks is often subtle, such as the tip of a screw being near a hole versus in the hole. Furthermore, these small differences are often only observable from certain viewpoints or may even require information from multiple viewpoints to fully ver…
Over the past decade, Monte Carlo Tree Search (MCTS) and specifically Upper Confidence Bound in Trees (UCT) have proven to be quite effective in large probabilistic planning domains. In this paper, we focus on how values are backpropagated in the MCTS tree, and apply complex return strategies from t…
We introduce a particle filter-based approach to representing and actively reducing uncertainty over articulated motion models. The presented method provides a probabilistic model that integrates visual observations with feedback from manipulation actions to best characterize a distribution of possi…
We introduce CHAMP, an algorithm for online Bayesian changepoint detection in settings where it is difficult or undesirable to integrate over the parameters of candidate models. CHAMP is used in combination with several articulation models to detect changes in articulated motion of objects in the wo…
We propose the Ω-return as an alternative to the λ-return currently used by the TD(λ) family of algorithms. The benefit of the Ω-return is that it accounts for the correlation of different length returns. Because it is difficult to compute exactly, we suggest one way of approximating the Ω-return. W…