Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.00977 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912995710337024 |
|---|---|
| author | Hao, Ruijie Zhang, Longfei Dai, Yang Ma, Yang Liang, Xingxing Cheng, Guangquan |
| author_facet | Hao, Ruijie Zhang, Longfei Dai, Yang Ma, Yang Liang, Xingxing Cheng, Guangquan |
| contents | Reinforcement Learning (RL) has proven highly effective in addressing complex control and decision-making tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution, which constrains the policy from capturing multimodal distributions, making it difficult to cover the full range of optimal solutions in multi-solution problems, and the return is reduced to a mean value, losing its multimodal nature and thus providing insufficient guidance for policy updates. In response to these problems, we propose a RL algorithm termed flow-based policy with distributional RL (FP-DRL). This algorithm models the policy using flow matching, which offers both computational efficiency and the capacity to fit complex distributions. Additionally, it employs a distributional RL approach to model and optimize the entire return distribution, thereby more effectively guiding multimodal policy updates and improving agent performance. Experimental trails on MuJoCo benchmarks demonstrate that the FP-DRL algorithm achieves state-of-the-art (SOTA) performance in most MuJoCo control tasks while exhibiting superior representation capability of the flow policy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_00977 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Flow-based Policy With Distributional Reinforcement Learning in Trajectory Optimization Hao, Ruijie Zhang, Longfei Dai, Yang Ma, Yang Liang, Xingxing Cheng, Guangquan Machine Learning Artificial Intelligence Reinforcement Learning (RL) has proven highly effective in addressing complex control and decision-making tasks. However, in most traditional RL algorithms, the policy is typically parameterized as a diagonal Gaussian distribution, which constrains the policy from capturing multimodal distributions, making it difficult to cover the full range of optimal solutions in multi-solution problems, and the return is reduced to a mean value, losing its multimodal nature and thus providing insufficient guidance for policy updates. In response to these problems, we propose a RL algorithm termed flow-based policy with distributional RL (FP-DRL). This algorithm models the policy using flow matching, which offers both computational efficiency and the capacity to fit complex distributions. Additionally, it employs a distributional RL approach to model and optimize the entire return distribution, thereby more effectively guiding multimodal policy updates and improving agent performance. Experimental trails on MuJoCo benchmarks demonstrate that the FP-DRL algorithm achieves state-of-the-art (SOTA) performance in most MuJoCo control tasks while exhibiting superior representation capability of the flow policy. |
| title | Flow-based Policy With Distributional Reinforcement Learning in Trajectory Optimization |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2604.00977 |