Related papers: Learning Preferences for Manipulation Tasks from O…

Deep reinforcement learning has achieved impressive successes yet often requires a very large amount of interaction data. This result is perhaps unsurprising, as using complicated function approximation often requires more data to fit, and…

Generating complex behaviors that satisfy the preferences of non-expert users is a crucial requirement for AI agents. Interactive reward learning from trajectory comparisons (a.k.a. RLHF) is one way to allow non-expert users to convey…

Reinforcement learning with human feedback (RLHF), which learns a reward model from human preference data and then optimizes a policy to favor preferred responses, has emerged as a central paradigm for aligning large language models (LLMs)…

Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize…

This paper presents a new learning framework that leverages the knowledge from imitation learning, deep reinforcement learning, and control theories to achieve human-style locomotion that is natural, dynamic, and robust for humanoids. We…

Learning control policies to perform complex robotics tasks from human preference data presents significant challenges. On the one hand, the complexity of such tasks typically requires learning policies to perform a variety of subtasks,…

Decision-making problems often feature uncertainty stemming from heterogeneous and context-dependent human preferences. To address this, we propose a sequential learning-and-optimization pipeline to learn preference distributions and…

A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this…

Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm in artificial intelligence to align large models with human preferences. In this paper, we propose a novel statistical framework to simultaneously conduct the…

Robots are expected to replace menial tasks such as housework. Some of these tasks include nonprehensile manipulation performed without grasping objects. Nonprehensile manipulation is very difficult because it requires considering the…

Interactive Machine Learning is concerned with creating systems that operate in environments alongside humans to achieve a task. A typical use is to extend or amplify the capabilities of a human in cognitive or physical ways, requiring the…

Robot motion planning often requires finding trajectories that balance different user intents, or preferences. One of these preferences is usually arrival at the goal, while another might be obstacle avoidance. Here, we formalize these, and…

Transformers have demonstrated exceptional performance across a wide range of domains. While their ability to perform reinforcement learning in-context has been established both theoretically and empirically, their behavior in…

We study the problem of online learning in a class of Markov decision processes known as linearly solvable MDPs. In the stationary version of this problem, a learner interacts with its environment by directly controlling the state…

Learning a reward function from human preferences is challenging as it typically requires having a high-fidelity simulator or using expensive and potentially unsafe actual physical rollouts in the environment. However, in many tasks the…

Predicting the output of a dynamical system from streaming data is fundamental to real-time feedback control and decision-making. We first derive an autoregressive representation that relates future local outputs to asynchronous past…

A contextual bandit problem is studied in a highly non-stationary environment, which is ubiquitous in various recommender systems due to the time-varying interests of users. Two models with disjoint and hybrid payoffs are considered to…

User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data. Among existing user behavior modeling solutions, attention networks are…

What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised Environment Design (UED) methods have gained recent attention…

Mutual adaptation can significantly enhance overall task performance in human-robot co-transportation by integrating both the robot's and human's understanding of the environment. While human modeling helps capture humans' subjective…