Clustering-based Failed goal Aware Hindsight Experience Replay
In a multi-goal reinforcement learning environment, an agent learns a policy to perform tasks with multiple goals from experiences gained through exploration. In environments with sparse binary rewards, the replay buffer contains few successful experiences, posing a challenge for sampling efficiency...
Na minha lista:
| Principais autores: | , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado em: |
PeerJ Inc.
2024-12-01
|
| Colecção: | PeerJ Computer Science |
| Assuntos: | |
| Acesso em linha: | https://peerj.com/articles/cs-2588.pdf |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|