IEEE Access | |
Off-Policy Meta-Reinforcement Learning With Belief-Based Task Inference | |
Yoshimasa Tsuruoka1  Takahisa Imagawa1  Takuya Hiraoka1  | |
[1] National Institute of Advanced Industrial Science and Technology, Tokyo, Japan; | |
关键词: Artificial intelligence; inference; meta learning; reinforcement learning; uncertainty; | |
DOI : 10.1109/ACCESS.2022.3170582 | |
来源: DOAJ |
【 摘 要 】
Meta-reinforcement learning (RL) addresses the problem of sample inefficiency in deep RL by using experience obtained in past tasks for solving a new task. However, most existing meta-RL methods require partially or fully on-policy data, which hinders the improvement of sample efficiency. To alleviate this problem, we propose a novel off-policy meta-RL method,
【 授权许可】
Unknown