← Back to all news
arXiv Machine Learning By Jo\~ao A. C\^andido Ramos, Lionel Blond\'e, Hugues Vinzant, Jacopo Castellini, Alexandros Kalousis

FOCUS: First-Order Control Using Optimal Transport Supervision for Imitation from Observations

Read the original on arXiv Machine Learning →

FOCUS is a new imitation‑learning method that learns from state‑only demonstrations without temporal alignment. It uses local optimal‑transport alignment to match short agent rollouts with sampled expert segments, creating differentiable imitation rewards. A learned critic then bootstraps value beyond the rollout horizon, improving sample efficiency and training stability on contact‑rich locomotion tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Oct 1

SynIL: Leveraging Synergy for Offline Imitation Learning from Imperfect Demonstration Datasets

SynIL is a new framework for offline imitation learning that automatically assesses the quality of demonstration data without requiring labels. It uses motor synergy—a low‑dimensional coordinated movement pattern linked to proficiency—to generate dense, transition‑level reward signals through self‑supervised reward regression. Experiments on D4RL locomotion and Robomimic manipulation datasets show that synergy‑derived rewards align well with true rewards and that SynIL outperforms Behavior Cloning and rivals or surpasses offline reinforcement learning in sparse‑reward scenarios.

By Yuto Tanaka, Kyo Kutsuzawa, Martina Doku, Dai Owaki, Mitsuhiro Hayashibe
reinforcement-learningroboticsbenchmarks
More like this →
arXiv Computer Vision
Sep 21

DexPIE: Stable Dexterous Policy Improvement from Real-World Experience

DexPIE is a post‑training framework that improves dexterous manipulation policies using real‑world experience. It introduces a dexterous‑hand‑adapted intervention system and multi‑stage DAgger‑style data collection to enhance exploration, aligns training and inference to reduce distribution shift, and conditions the policy on a continuous optimality indicator for fine‑grained data quality use. In three real‑world tasks, DexPIE boosts success rates by 37.3% over a demonstration‑based baseline, outperforming all other methods and showing stronger robustness.

By Ruizhe Liao, Wenrui Chen, Liangji Zeng, Haoran Lin, Fan Yang, Kailun Yang, Yaonan Wang
robotics
More like this →