发帖
雷达卡
Offline Meta-Reinforcement Learning with Advantage Weighting
Eric Mitchell 1 Rafael Rafailov 1 Xue Bin Peng 2 Sergey Levine 2 Chelsea Finn 1
Abstract of reinforcement learning algorithms, when the goal is to
ultimately learn many tasks. Meta-RL algorithms exploit
This paper introduces the offline meta- shared structure among tasks during meta-training, amor-
reinforcement learning (offline meta-RL) ...
京公网安备 11010802022788号
