research
∙
07/01/2023
DoReMi: Grounding Language Model by Detecting and Recovering from Plan-Execution Misalignment
Large language models encode a vast amount of semantic knowledge and pos...
share
research
∙
06/30/2023
Decentralized Motor Skill Learning for Complex Robotic Systems
Reinforcement learning (RL) has achieved remarkable success in complex r...
research
∙
12/03/2022
Reinforcement learning with Demonstrations from Mismatched Task under Sparse Reward
Reinforcement learning often suffer from the sparse reward issue in real...
research
∙
10/01/2022