The paper introduces Diffusion-Augmented Markov Decision Processes (DA‑MDPs), a framework that extends Maximum Entropy Reinforcement Learning to diffusion-based policies. DA‑MDPs treat each reverse‑diffusion step as an RL decision, deriving a tractable reverse‑KL bound that decomposes across denoising transitions and yields diffusion‑augmented soft rewards, value functions, and policy objectives. The authors implement this framework with PPO, REPPO, and a maximum‑entropy WPO variant, showing improved continuous‑control performance, higher success rates on manipulation tasks, and memory‑efficient training with action chunking.
By Sebastian Sanokowski, Kaustubh Patil, Majid Khadiv
arXiv:2608.23664v1 Announce Type: cross
Abstract: Reward fine-tuning is becoming an important tool for adapting diffusion models to human preferences and task-specific objectives, but existing method...
By Jaemoo Choi, Wei Guo, Yuchen Zhu, Arash Vahdat, Molei Tao, Julius Berner, Yongxin Chen
arXiv:2607. 07693v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for aligning generative models with human preferences.
By Eric Zhu, Abhinav Shrivastava, Soumik Mukhopadhyay
arXiv:2606. 10825v1 Announce Type: new Abstract: Diffusion policies (DPs) have emerged as expressive policy representations for robot learning, often used with imitation learning methods such as behavioral cloning (BC).
By Zakariae El Asri, Philippe Gratias-Quiquandon, Nicolas Thome, Olivier Sigaud
arXiv:2609.06882v1 Announce Type: cross
Abstract: Diffusion policies offer a powerful and expressive parameterization for continuous control. Yet, their integration with reinforcement learning remain...
By Mahmoud Selim, Cristina Cipriani, Karl H. Johansson
arXiv:2606. 08602v1 Announce Type: cross Abstract: We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems.
By Boshu Lei, Kostas Daniilidis, Antonio Loquercio
arXiv:2607. 14522v1 Announce Type: new Abstract: We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control approach, where the state dynamics are modeled as a controlled continuous-time Markov chain (CTMC).
By Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang
The paper introduces Bidirectional Behavior Prior Distillation (B2PD), a method that uses action‑value priors to train a conditional variational autoencoder for generating high‑value behavior support. These expert behavior priors are then distilled into the online reinforcement learning agent, reducing inefficient exploration and stabilizing policy updates. Experiments on state‑ and pixel‑based tasks show that B2PD improves sample efficiency while maintaining stable learning dynamics.
By Gong Gao, Xiao Lai, Jiaji Shen, Ning Jia, Xianhui Liu, Weidong Zhao
arXiv:2602. 07339v2 Announce Type: replace Abstract: Diffusion-based trajectory planners can model multi-modal driving behavior, but their iterative denoising process introduces a latency bottleneck for real-time closed-loop deployment.
By Ruturaj Reddy, Hrishav Bakul Barua, Junn Yong Loo, Thanh Thi Nguyen, Ganesh Krishnasamy
arXiv:2606. 15260v1 Announce Type: cross Abstract: Reinforcement learning with massively parallel simulations has become a standard framework for developing robust, deployable policies; however, most existing approaches still rely on simple Gaussian policy parameterizations.
By Huy Le, Onur Celik, Denis Blessing, Tai Hoang, Claas A Voelcker, Axel Brunnbauer, Felix Richter, Michael Volpp, Gerhard Neumann
arXiv:2609.36393v1 Announce Type: cross
Abstract: Traditional reinforcement learning (RL) techniques focus on maximizing expected cumulative reward, where each action assumes to take a constant unit...
By Muhang Tian, Sherry Yang
arXiv:2606. 27766v1 Announce Type: cross Abstract: Offline reinforcement learning enables policy learning from fixed datasets without additional environment interaction, making it appealing for safety-critical applications where online exploration is costly or unsafe.
By Shiqiang Gong