Related papers: GIFT: Generalizing Intent for Flexible Test-Time R…

Designing reward functions is a challenging problem in AI and robotics. Humans usually have a difficult time directly specifying all the desirable behaviors that a robot needs to optimize. One common approach is to learn reward functions…

Natural language is often the easiest and most convenient modality for humans to specify tasks for robots. However, learning to ground language to behavior typically requires impractical amounts of diverse, language-annotated demonstrations…

Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous…

This paper explores how deliberate mutations of reward function in reinforcement learning can produce diversified skill variations in robotic manipulation tasks, examined with a liquid pouring use case. To this end, we developed a new…

Recent advances in reinforcement learning have inspired increasing interest in learning user modeling adaptively through dynamic interactions, e.g., in reinforcement learning based recommender systems. Reward function is crucial for most of…

As robots enter human environments, they will be expected to accomplish a tremendous range of tasks. It is not feasible for robot designers to pre-program these behaviors or know them in advance, so one way to address this is through…

Learning diverse skills without hand-crafted reward functions could accelerate reinforcement learning in downstream tasks. However, existing skill discovery methods focus solely on maximizing the diversity of skills without considering…

Motivated by the intuitive understanding humans have about the space of possible interactions, and the ease with which they can generalize this understanding to previously unseen scenes, we develop an approach for learning visual…

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…

Reinforcement learning (RL) is a popular approach for robotic path planning in uncertain environments. However, the control policies trained for an RL agent crucially depend on user-defined, state-based reward functions. Poorly designed…

We propose a novel system for robot-to-human object handover that emulates human coworker interactions. Unlike most existing studies that focus primarily on grasping strategies and motion planning, our system focus on 1. inferring human…

Addressing the issues of who saying what to whom in multi-party conversations (MPCs) has recently attracted a lot of research attention. However, existing methods on MPC understanding typically embed interlocutors and utterances into…

Imitation learning (IL) is a framework that learns to imitate expert behavior from demonstrations. Recently, IL shows promising results on high dimensional and control tasks. However, IL typically suffers from sample inefficiency in terms…

We focus on learning the desired objective function for a robot. Although trajectory demonstrations can be very informative of the desired objective, they can also be difficult for users to provide. Answers to comparison queries, asking…

Learning from Demonstrations (LfD) and Reinforcement Learning (RL) have enabled robot agents to accomplish complex tasks. Reward Machines (RMs) enhance RL's capability to train policies over extended time horizons by structuring high-level…

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…

Agents trained via deep reinforcement learning (RL) routinely fail to generalize to unseen environments, even when these share the same underlying dynamics as the training levels. Understanding the generalization properties of RL is one of…

Physical interactions can often help reveal information that is not readily apparent. For example, we may tug at a table leg to evaluate whether it is built well, or turn a water bottle upside down to check that it is watertight. We propose…

This paper investigates whether reward matching is a viable alternative to reward maximization methods for on-policy RL of LLMs. Group-relative Implicit Fine-Tuning (GIFT) is proposed, combining GRPO-style group sampling, DPO-style implicit…

When a robot learns from human examples, most approaches assume that the human partner provides examples of optimal behavior. However, there are applications in which the robot learns from non-expert humans. We argue that the robot should…