Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2208.14741 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917562924662784 |
|---|---|
| author | Kim, Taeyoung Har, Dongsoo |
| author_facet | Kim, Taeyoung Har, Dongsoo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2208_14741 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Cluster-based Sampling in Hindsight Experience Replay for Robotic Tasks (Student Abstract) Kim, Taeyoung Har, Dongsoo Robotics Artificial Intelligence 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. |
| title | Cluster-based Sampling in Hindsight Experience Replay for Robotic Tasks (Student Abstract) |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2208.14741 |