TransDreamer: Reinforcement Learning with Transformer World Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913580463423488 |
|---|---|
| author | Chen, Chang Wu, Yi-Fu Yoon, Jaesik Ahn, Sungjin |
| author_facet | Chen, Chang Wu, Yi-Fu Yoon, Jaesik Ahn, Sungjin |
| contents | The Dreamer agent provides various benefits of Model-Based Reinforcement Learning (MBRL) such as sample efficiency, reusable knowledge, and safe planning. However, its world model and policy networks inherit the limitations of recurrent neural networks and thus an important question is how an MBRL framework can benefit from the recent advances of transformers and what the challenges are in doing so. In this paper, we propose a transformer-based MBRL agent, called TransDreamer. We first introduce the Transformer State-Space Model, a world model that leverages a transformer for dynamics predictions. We then share this world model with a transformer-based policy network and obtain stability in training a transformer-based RL agent. In experiments, we apply the proposed model to 2D visual RL and 3D first-person visual RL tasks both requiring long-range memory access for memory-based reasoning. We show that the proposed model outperforms Dreamer in these complex tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2202_09481 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | TransDreamer: Reinforcement Learning with Transformer World Models Chen, Chang Wu, Yi-Fu Yoon, Jaesik Ahn, Sungjin Machine Learning The Dreamer agent provides various benefits of Model-Based Reinforcement Learning (MBRL) such as sample efficiency, reusable knowledge, and safe planning. However, its world model and policy networks inherit the limitations of recurrent neural networks and thus an important question is how an MBRL framework can benefit from the recent advances of transformers and what the challenges are in doing so. In this paper, we propose a transformer-based MBRL agent, called TransDreamer. We first introduce the Transformer State-Space Model, a world model that leverages a transformer for dynamics predictions. We then share this world model with a transformer-based policy network and obtain stability in training a transformer-based RL agent. In experiments, we apply the proposed model to 2D visual RL and 3D first-person visual RL tasks both requiring long-range memory access for memory-based reasoning. We show that the proposed model outperforms Dreamer in these complex tasks. |
| title | TransDreamer: Reinforcement Learning with Transformer World Models |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2202.09481 |