Diffusion Models for Reinforcement Learning: A Survey
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914689452081152 |
|---|---|
| author | Zhu, Zhengbang Zhao, Hanye He, Haoran Zhong, Yichao Zhang, Shenyu Guo, Haoquan Chen, Tingting Zhang, Weinan |
| author_facet | Zhu, Zhengbang Zhao, Hanye He, Haoran Zhong, Yichao Zhang, Shenyu Guo, Haoquan Chen, Tingting Zhang, Weinan |
| contents | Diffusion models surpass previous generative models in sample quality and training stability. Recent works have shown the advantages of diffusion models in improving reinforcement learning (RL) solutions. This survey aims to provide an overview of this emerging field and hopes to inspire new avenues of research. First, we examine several challenges encountered by RL algorithms. Then, we present a taxonomy of existing methods based on the roles of diffusion models in RL and explore how the preceding challenges are addressed. We further outline successful applications of diffusion models in various RL-related tasks. Finally, we conclude the survey and offer insights into future research directions. We are actively maintaining a GitHub repository for papers and other related resources in utilizing diffusion models in RL: https://github.com/apexrl/Diff4RLSurvey. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_01223 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Diffusion Models for Reinforcement Learning: A Survey Zhu, Zhengbang Zhao, Hanye He, Haoran Zhong, Yichao Zhang, Shenyu Guo, Haoquan Chen, Tingting Zhang, Weinan Machine Learning Artificial Intelligence Diffusion models surpass previous generative models in sample quality and training stability. Recent works have shown the advantages of diffusion models in improving reinforcement learning (RL) solutions. This survey aims to provide an overview of this emerging field and hopes to inspire new avenues of research. First, we examine several challenges encountered by RL algorithms. Then, we present a taxonomy of existing methods based on the roles of diffusion models in RL and explore how the preceding challenges are addressed. We further outline successful applications of diffusion models in various RL-related tasks. Finally, we conclude the survey and offer insights into future research directions. We are actively maintaining a GitHub repository for papers and other related resources in utilizing diffusion models in RL: https://github.com/apexrl/Diff4RLSurvey. |
| title | Diffusion Models for Reinforcement Learning: A Survey |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2311.01223 |