Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2021
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2112.02817 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909106516787200 |
|---|---|
| author | Hao, Jianye Yuan, Yifu Wang, Cong Wang, Zhen |
| author_facet | Hao, Jianye Yuan, Yifu Wang, Cong Wang, Zhen |
| contents | Model-based reinforcement learning (MBRL) achieves significant sample efficiency in practice in comparison to model-free RL, but its performance is often limited by the existence of model prediction error. To reduce the model error, standard MBRL approaches train a single well-designed network to fit the entire environment dynamics, but this wastes rich information on multiple sub-dynamics which can be modeled separately, allowing us to construct the world model more accurately. In this paper, we propose the Environment Dynamics Decomposition (ED2), a novel world model construction framework that models the environment in a decomposing manner. ED2 contains two key components: sub-dynamics discovery (SD2) and dynamics decomposition prediction (D2P). SD2 discovers the sub-dynamics in an environment automatically and then D2P constructs the decomposed world model following the sub-dynamics. ED2 can be easily combined with existing MBRL algorithms and empirical results show that ED2 significantly reduces the model error, increases the sample efficiency, and achieves higher asymptotic performance when combined with the state-of-the-art MBRL algorithms on various continuous control tasks. Our code is open source and available at https://github.com/ED2-source-code/ED2. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2112_02817 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | ED2: Environment Dynamics Decomposition World Models for Continuous Control Hao, Jianye Yuan, Yifu Wang, Cong Wang, Zhen Machine Learning Artificial Intelligence Model-based reinforcement learning (MBRL) achieves significant sample efficiency in practice in comparison to model-free RL, but its performance is often limited by the existence of model prediction error. To reduce the model error, standard MBRL approaches train a single well-designed network to fit the entire environment dynamics, but this wastes rich information on multiple sub-dynamics which can be modeled separately, allowing us to construct the world model more accurately. In this paper, we propose the Environment Dynamics Decomposition (ED2), a novel world model construction framework that models the environment in a decomposing manner. ED2 contains two key components: sub-dynamics discovery (SD2) and dynamics decomposition prediction (D2P). SD2 discovers the sub-dynamics in an environment automatically and then D2P constructs the decomposed world model following the sub-dynamics. ED2 can be easily combined with existing MBRL algorithms and empirical results show that ED2 significantly reduces the model error, increases the sample efficiency, and achieves higher asymptotic performance when combined with the state-of-the-art MBRL algorithms on various continuous control tasks. Our code is open source and available at https://github.com/ED2-source-code/ED2. |
| title | ED2: Environment Dynamics Decomposition World Models for Continuous Control |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2112.02817 |