The paper investigates a natural gradient method based on the Fisher information matrix of state-action distributions, which follows a Fisher‑Rao gradient flow within the state-action polytope under a linear potential. It establishes linear convergence rates for Fisher‑Rao gradient flows of linear programs, with the rate tied to the program’s geometry, and provides improved error bounds for entropic regularization. Additionally, the authors extend their analysis to perturbed flows, proving sublinear convergence for both perturbed Fisher‑Rao and natural gradient flows, thereby encompassing state‑action natural policy gradients.
By Johannes M\"uller, Semih \c{C}ayc{\i}, Guido Mont\'ufar
arXiv:2608. 11052v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL) aims to recover a reward function under which the resulting policy reproduces the behavior observed in expert demonstrations.
By Nikita Sevriukov, Anna Barabanova, Uliana Gagarina, Karina Ivanova, Sofiia Kasaeva, Ilya Levin, Marina Sheshukova
The paper investigates how reinforcement learning can be effectively applied to diffusion models for visual tasks, focusing on the role of likelihood estimation. By systematically separating policy‑gradient objectives, likelihood estimators, and rollout sampling schemes, the authors find that using an evidence lower bound (ELBO) based likelihood estimator computed from the final generated sample is the key factor for stable and efficient RL optimization, outweighing the choice of loss function. Experiments on SD 3.5 Medium across multiple reward benchmarks confirm that this approach improves GenEval scores from 0.24 to 0.95 in 90 GPU hours, outperforming existing methods such as FlowGRPO and the current state‑of‑the‑art without reward hacking.
By Jaemoo Choi, Yuchen Zhu, Wei Guo, Petr Molodyk, Bo Yuan, Jinbin Bai, Yi Xin, Molei Tao, Yongxin Chen
arXiv:2606. 05888v1 Announce Type: new Abstract: Retry-based objectives such as pass@K and max@K optimize the best return obtained from multiple sampled trajectories, and recent work has shown that they can promote exploration without explicit exploration bonuses.
By Soichiro Nishimori, Paavo Parmas
arXiv:2601. 23075v2 Announce Type: replace Abstract: On-policy Reinforcement Learning (RL) remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are noisy, and policy updates must be conservative.
By Yuexin Bian, Jie Feng, Tao Wang, Yijiang Li, Sicun Gao, Yuanyuan Shi
arXiv:2608. 03967v1 Announce Type: cross Abstract: Generative Flow Networks (GFlowNets) have emerged as a flexible framework for amortised inference over discrete and mixed discrete-continuous objects, requiring only an unnormalised target density specified through a reward.
By Yordan Raykov, Rodrigo Veiga
arXiv:2607. 28390v1 Announce Type: new Abstract: Constrained Markov Decision Processes (CMDPs) provide a natural framework for reinforcement learning in safety-critical applications, where agents maximize long-term reward while satisfying long-term constraints.
By Ankur Naskar, Vaneet Aggarwal
arXiv:2606. 15793v1 Announce Type: cross Abstract: This paper explores policy gradient algorithms for training stochastic policies to sample from structured discrete probability distributions under the Generative Flow Network (GFlowNet) framework.
By Anna Zykova-Myzina, Timofei Gritsaev, Daniil Tiapkin, Nikita Morozov
arXiv:2602. 05379v2 Announce Type: replace-cross Abstract: Effective reinforcement learning (RL) for complex stochastic systems requires leveraging historical data to improve sample efficiency and accelerate policy optimization.
By Hua Zheng, Wei Xie, M. Ben Feng, Keilung Choy
arXiv:2606. 30376v1 Announce Type: new Abstract: Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods.
By Zheming Fu, Ruizhe He, Wei Shang, Xiaoxiao Ma, Lei Wang, Chang Liu, Siming Fu
arXiv:2609.31882v2 Announce Type: replace-cross
Abstract: Reward-based diffusion fine-tuning faces practical challenges when desirable outcomes are rare or conditioning corrections are costly to esti...
By Zhengyi Guo, Jiayuan Sheng, Wenpin Tang, David D. Yao
arXiv:2606. 06080v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards is widely used for post-training reasoning models, but sparse outcome rewards make exploration difficult.
By Shota Takashiro, Soichiro Nishimori, Paavo Parmas, Yongmin Kim, Kohsei Matsutani, Gouki Minegishi, Yusuke Iwasawa, Takeshi Kojima, Yutaka Matsuo