A Survey on Transformers in Reinforcement Learning
Abstract
Transformer has been considered the dominating neural architecture in NLP and CV, mostly under supervised settings. Recently, a similar surge of using Transformers has appeared in the domain of reinforcement learning (RL), but it is faced with unique design choices and challenges brought by the nature of RL. However, the evolution of Transformers in RL has not yet been well unraveled. In this paper, we seek to systematically review motivations and progress on using Transformers in RL, provide a taxonomy on existing works, discuss each sub-field, and summarize future prospects.
Cite
Text
Li et al. "A Survey on Transformers in Reinforcement Learning." Transactions on Machine Learning Research, 2023.Markdown
[Li et al. "A Survey on Transformers in Reinforcement Learning." Transactions on Machine Learning Research, 2023.](https://mlanthology.org/tmlr/2023/li2023tmlr-survey/)BibTeX
@article{li2023tmlr-survey,
title = {{A Survey on Transformers in Reinforcement Learning}},
author = {Li, Wenzhe and Luo, Hao and Lin, Zichuan and Zhang, Chongjie and Lu, Zongqing and Ye, Deheng},
journal = {Transactions on Machine Learning Research},
year = {2023},
url = {https://mlanthology.org/tmlr/2023/li2023tmlr-survey/}
}