paper-with-me

홈 › Papers

Robot Policy Learning with Temporal Optimal Transport Reward

2024-10-29 · Yuwei Fu, Haichao Zhang, Di wu, Wei Xu, Benoit Boulet

Reward specification is one of the most tricky problems in Reinforcement Learning, which usually requires tedious hand engineering in practice. One promising approach to tackle this challenge is to adopt existing expert video demonstrations for policy learning. Some recent work investigates how to learn robot policies from only a single/few expert video demonstrations. For example, reward labeling via Optimal Transport (OT) has been shown to be an effective strategy to generate a proxy reward by measuring the alignment between the robot trajectory and the expert demonstrations. However, previous work mostly overlooks that the OT reward is invariant to temporal order information, which could bring extra noise to the reward signal. To address this issue, in this paper, we introduce the Temporal Optimal Transport (TemporalOT) reward to incorporate temporal order information for learning a more accurate OT-based proxy reward. Extensive experiments on the Meta-world benchmark tasks validate the efficacy of the proposed method. Code is available at: https://github.com/fuyw/TemporalOT

📄 PDF Abstract BibTeX arXiv:2410.21795

Code (1)

fuyw/temporalot 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environments

2023-10-13 · Maryam Zare, Parham M. Kebria, Abbas Khosravi

Most Reinforcement Learning (RL) methods are traditionally studied in an active learning setting, where agents directly interact with their environments, observe action outcomes, and learn through trial and error. Howeve…

Active LearningOffline RLReinforcement Learning (RL)

Watch and Match: Supercharging Imitation with Regularized Optimal Transport

2022-06-30 · Siddhant Haldar, Vaibhav Mathur, Denis Yarats, Lerrel Pinto

Imitation learning holds tremendous promise in learning policies efficiently for complex decision making problems. Current state-of-the-art algorithms often use inverse reinforcement learning (IRL), where given a set of …

Decision MakingImitation Learning

Wasserstein Adversarial Imitation Learning

2019-06-19 · Huang Xiao, Michael Herman, Joerg Wagner, Sebastian Ziesche 외

Imitation Learning describes the problem of recovering an expert policy from demonstrations. While inverse reinforcement learning approaches are known to be very sample-efficient in terms of expert demonstrations, they u…

Imitation Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Renaissance Robot: Optimal Transport Policy Fusion for Learning Diverse Skills

2022-07-03 · Julia Tan, Ransalu Senanayake, Fabio Ramos

Deep reinforcement learning (RL) is a promising approach to solving complex robotics problems. However, the process of learning through trial-and-error interactions is often highly time-consuming, despite recent advancem…

Deep Reinforcement LearningReinforcement Learning (RL)

Reinforcement Learning for Flow-Matching Policies with Density Transport

2026-06-07 · Boshu Lei, Kostas Daniilidis, Antonio Loquercio arxiv

We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems. Our key insight is to view RL-based policy improvement as a transport of action densities …

Reinforcement LearningRobot Manipulation