Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2410.11359 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910651235958784 |
|---|---|
| author | Jiang, Eric Hanchen Zhang, Zhi Zhang, Dinghuai Lizarraga, Andrew Xu, Chenheng Zhang, Yasi Zhao, Siyan Xu, Zhengjie Yu, Peiyu Tang, Yuer Kong, Deqian Wu, Ying Nian |
| author_facet | Jiang, Eric Hanchen Zhang, Zhi Zhang, Dinghuai Lizarraga, Andrew Xu, Chenheng Zhang, Yasi Zhao, Siyan Xu, Zhengjie Yu, Peiyu Tang, Yuer Kong, Deqian Wu, Ying Nian |
| contents | Advancements in reinforcement learning have led to the development of sophisticated models capable of learning complex decision-making tasks. However, efficiently integrating world models with decision transformers remains a challenge. In this paper, we introduce a novel approach that combines the Dreamer algorithm's ability to generate anticipatory trajectories with the adaptive learning strengths of the Online Decision Transformer. Our methodology enables parallel training where Dreamer-produced trajectories enhance the contextual decision-making of the transformer, creating a bidirectional enhancement loop. We empirically demonstrate the efficacy of our approach on a suite of challenging benchmarks, achieving notable improvements in sample efficiency and reward maximization over existing methods. Our results indicate that the proposed integrated framework not only accelerates learning but also showcases robustness in diverse and dynamic scenarios, marking a significant step forward in model-based reinforcement learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11359 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting Jiang, Eric Hanchen Zhang, Zhi Zhang, Dinghuai Lizarraga, Andrew Xu, Chenheng Zhang, Yasi Zhao, Siyan Xu, Zhengjie Yu, Peiyu Tang, Yuer Kong, Deqian Wu, Ying Nian Machine Learning Robotics Advancements in reinforcement learning have led to the development of sophisticated models capable of learning complex decision-making tasks. However, efficiently integrating world models with decision transformers remains a challenge. In this paper, we introduce a novel approach that combines the Dreamer algorithm's ability to generate anticipatory trajectories with the adaptive learning strengths of the Online Decision Transformer. Our methodology enables parallel training where Dreamer-produced trajectories enhance the contextual decision-making of the transformer, creating a bidirectional enhancement loop. We empirically demonstrate the efficacy of our approach on a suite of challenging benchmarks, achieving notable improvements in sample efficiency and reward maximization over existing methods. Our results indicate that the proposed integrated framework not only accelerates learning but also showcases robustness in diverse and dynamic scenarios, marking a significant step forward in model-based reinforcement learning. |
| title | DODT: Enhanced Online Decision Transformer Learning through Dreamer's Actor-Critic Trajectory Forecasting |
| topic | Machine Learning Robotics |
| url | https://arxiv.org/abs/2410.11359 |