This paper studies offline Imitation Learning (IL) where an agent learns to imitate an expert
demonstrator without additional online environment interactions. Instead, the learner is …

In supervised learning, the question of data quality and curation has been sidelined in
recent years in favor of increasingly more powerful and expressive models that can ingest …

Imitation learning (IL) algorithms excel in acquiring high-quality policies from expert data for
sequential decision-making tasks. But, their effectiveness is hampered when faced with …

We consider a Bayesian approach to offline model-based inverse reinforcement learning
(IRL). The proposed framework differs from existing offline model-based IRL approaches by …

Reward function specification, which requires considerable human effort and iteration,
remains a major impediment for learning behaviors through deep reinforcement learning. In …

Offline imitation learning (IL) promises the ability to learn performant policies from pre-
collected demonstrations without interactions with the environment. However, imitating …

In this paper, we propose a novel video depth estimation approach, FutureDepth, which
enables the model to implicitly leverage multi-frame and motion cues to improve depth …

Offline reinforcement learning (RL) provides a framework for learning decision-making from
offline data and therefore constitutes a promising approach for real-world applications such …

Offline imitation learning (IL) is a powerful method to solve decision-making problems from
expert demonstrations without reward labels. Existing offline IL methods suffer from severe …

We introduce a new benchmark, LLF-Bench (Learning from Language Feedback
Benchmark; pronounced as" elf-bench"), to evaluate the ability of AI agents to interactively …