Reward functions are difficult to design and often hard to align with human intent. Preference-
based Reinforcement Learning (RL) algorithms address these problems by learning reward …

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 …

Imitation learning methods seek to learn from an expert either through behavioral cloning
(BC) for the policy or inverse reinforcement learning (IRL) for the reward. Such methods …

In many domains, autoregressive models can attain high likelihood on the task of predicting
the next observation. However, this maximum-likelihood (MLE) objective does not …

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 …

Imitation Learning (IL) holds great promise for enabling agile locomotion in embodied
agents. However, many existing locomotion benchmarks primarily focus on simplified toy …

Imitation learning (IL) aims at producing agents that can imitate any behavior given a few
expert demonstrations. Yet existing approaches require many demonstrations and/or …

Humans often acquire new skills through observation and imitation. For robotic agents,
learning from the plethora of unlabeled video demonstration data available on the Internet …

Some Learning from Demonstrations (LfD) methods handle small mismatches in the action
spaces of the teacher and student. Here we address the case where the teacher's …

In this paper, we study offline-to-online Imitation Learning (IL) that pretrains an imitation
policy from static demonstration data, followed by fast finetuning with minimal environmental …