Cluster-based Sampling in Hindsight Experience Replay for Robotic Tasks (Student Abstract)
This work addresses sample inefficiency in robotic reinforcement learning, though it is incremental as it builds on existing hindsight experience replay methods.
The paper tackled the challenge of training agents in multi-goal reinforcement learning with sparse rewards by proposing a cluster-based sampling strategy for hindsight experience replay, which improved sample efficiency and achieved better performance than baselines in robotic control tasks.
In multi-goal reinforcement learning with a sparse binary reward, training agents is particularly challenging, due to a lack of successful experiences. To solve this problem, hindsight experience replay (HER) generates successful experiences even from unsuccessful ones. However, generating successful experiences from uniformly sampled ones is not an efficient process. In this paper, the impact of exploiting the property of achieved goals in generating successful experiences is investigated and a novel cluster-based sampling strategy is proposed. The proposed sampling strategy groups episodes with different achieved goals by using a cluster model and samples experiences in the manner of HER to create the training batch. The proposed method is validated by experiments with three robotic control tasks of the OpenAI Gym. The results of experiments demonstrate that the proposed method is substantially sample efficient and achieves better performance than baseline approaches.