Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914608037494784 |
|---|---|
| author | Sanokowski, Sebastian Patil, Kaustubh |
| author_facet | Sanokowski, Sebastian Patil, Kaustubh |
| contents | Diffusion models excel at sampling from complex, unnormalized distributions. In this work, we extend Maximum Entropy Reinforcement Learning (ME-RL) to diffusion processes, enabling sampling from the optimal policy trajectory distribution. By minimizing a tractable upper bound on the reverse KL divergence between the diffusion policy and the optimal policy trajectory distributions, we derive a modified surrogate objective and introduce Diffusion-Augmented Markov Decision Processes (DA-MDPs). DA-MDPs allow for seamless integration of diffusion policies into any ME-RL method with minimal modifications. We demonstrate its effectiveness by adapting Proximal Policy Optimization (PPO), Wasserstein Policy Optimization (WPO), and Relative Entropy Pathwise Policy Optimization (REPPO) into their diffusion-based variants: DA-MDP: PPO, DA-MDP: WPO, and DA-MDP: REPPO. Empirical results on standard continuous-control benchmarks show that our approach matches or outperforms baseline methods, while experiments on multimodal benchmarks confirm its ability to model multimodal action distributions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02019 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning Sanokowski, Sebastian Patil, Kaustubh Machine Learning Artificial Intelligence Diffusion models excel at sampling from complex, unnormalized distributions. In this work, we extend Maximum Entropy Reinforcement Learning (ME-RL) to diffusion processes, enabling sampling from the optimal policy trajectory distribution. By minimizing a tractable upper bound on the reverse KL divergence between the diffusion policy and the optimal policy trajectory distributions, we derive a modified surrogate objective and introduce Diffusion-Augmented Markov Decision Processes (DA-MDPs). DA-MDPs allow for seamless integration of diffusion policies into any ME-RL method with minimal modifications. We demonstrate its effectiveness by adapting Proximal Policy Optimization (PPO), Wasserstein Policy Optimization (WPO), and Relative Entropy Pathwise Policy Optimization (REPPO) into their diffusion-based variants: DA-MDP: PPO, DA-MDP: WPO, and DA-MDP: REPPO. Empirical results on standard continuous-control benchmarks show that our approach matches or outperforms baseline methods, while experiments on multimodal benchmarks confirm its ability to model multimodal action distributions. |
| title | Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2512.02019 |