Meta-reinforcement learning (meta-RL) algorithms allow for agents to learn new behaviors from small amounts of experience, mitigating the sample inefficiency problem in RL. However, while meta-RL agents can adapt quickly to new tasks at test time after experiencing only a few trajectories, the meta-training process is still sample-inefficient. Prior works have found that in the multi-task RL setting, relabeling past transitions and thus sharing experience among tasks can improve sample efficiency and asymptotic performance. We apply this idea to the meta-RL setting and devise a new relabeling method called Hindsight Foresight Relabeling (HFR). We construct a relabeling distribution using the combination of "hindsight", which is used to relabel trajectories using reward functions from the training task distribution, and "foresight", which takes the relabeled trajectories and computes the utility of each trajectory for each task. HFR is easy to implement and readily compatible with existing meta-RL algorithms. We find that HFR improves performance when compared to other relabeling methods on a variety of meta-RL tasks.

翻译：元强化学习( meta- RL) 算法允许代理商从少量经验中学习新的行为, 减轻RL 中的抽样低效率问题。 然而, 元RL 代理商在只经历几条轨迹之后, 可以在测试时间快速适应新的任务。 但是, 元RL 代理商在只经历几条轨迹之后, 元培训过程仍然缺乏样本效率。 先前的工程发现, 在多任务RL 设置中, 重新标签过去的过渡, 从而在任务之间分享经验, 可以提高样本效率和效果。 我们把这个想法应用到元RL 设置中, 并设计出一种新的重新标签方法, 叫做 Hindsight 前景重标签。 我们用“ 黑洞” 组合来构建一个重新标签分布, 用于使用培训任务分布的奖励功能重新标签轨迹, 以及“ 展望” 组合, 将重新标签的轨迹标为每条轨迹, 并计算每项任务的轨迹的实用性。 我们发现, HFRRR很容易实施, 并且很容易与现有的元RL 矩阵算法 比较时, 我们发现 HFRFRL 改进了其他任务 。