English
Related papers

Related papers: Improving DAPO from a Mixed-Policy Perspective

200 papers

Policy gradient methods, which have been extensively studied in the last decade, offer an effective and efficient framework for reinforcement learning problems. However, their performances can often be unsatisfactory, suffering from…

Machine Learning · Computer Science 2026-01-27 Shihab Ahmed , El Houcine Bergou , Aritra Dutta , Yue Wang

Large Language Models (LLMs) are increasingly aligned with human preferences through Reinforcement Learning from Human Feedback (RLHF). Among RLHF methods, Group Relative Policy Optimization (GRPO) has gained attention for its simplicity…

Computation and Language · Computer Science 2025-09-25 Yuhang Zhou , Jing Zhu , Shengyi Qian , Zhuokai Zhao , Xiyao Wang , Xiaoyu Liu , Ming Li , Paiheng Xu , Wei Ai , Furong Huang

Policy optimization methods are powerful algorithms in Reinforcement Learning (RL) for their flexibility to deal with policy parameterization and ability to handle model misspecification. However, these methods usually suffer from slow…

Machine Learning · Computer Science 2023-06-19 Yunfan Li , Yiran Wang , Yu Cheng , Lin Yang

Proximal policy optimization (PPO) has yielded state-of-the-art results in policy search, a subfield of reinforcement learning, with one of its key points being the use of a surrogate objective function to restrict the step size at each…

Machine Learning · Computer Science 2020-12-07 Wangshu Zhu , Andre Rosendo

Decentralized policy optimization has been commonly used in cooperative multi-agent tasks. However, since all agents are updating their policies simultaneously, from the perspective of individual agents, the environment is non-stationary,…

Machine Learning · Computer Science 2023-02-17 Hao Luo , Jiechuan Jiang , Zongqing Lu

Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of individual tokens or entire response sequences. However, such formulations often misalign with the natural…

Artificial Intelligence · Computer Science 2026-05-08 Lei Gao , Zhuoming Li , Mengxi Jia , Jiakang Yuan , Hongbo Sun , Hao Sun , Xuelong Li

Recent advances in reinforcement learning, such as Dynamic Sampling Policy Optimization (DAPO), show strong performance when paired with large language models (LLMs). Motivated by this success, we ask whether similar gains can be realized…

Computational Engineering, Finance, and Science · Computer Science 2025-05-27 Ruijian Zha , Bojun Liu

Recently, a novel class of Approximate Policy Iteration (API) algorithms have demonstrated impressive practical performance (e.g., ExIt from [2], AlphaGo-Zero from [27]). This new family of algorithms maintains, and alternately optimizes,…

Machine Learning · Computer Science 2019-04-09 Wen Sun , Geoffrey J. Gordon , Byron Boots , J. Andrew Bagnell

Offline reinforcement learning agents face significant deployment challenges due to the synthetic-to-real distribution mismatch. While most prior research has focused on improving the fidelity of synthetic sampling and incorporating…

Machine Learning · Computer Science 2025-10-01 Chi Zhou , Wang Luo , Haoran Li , Congying Han , Tiande Guo , Zicheng Zhang

Policy gradient methods ignore the potential value of adjusting environment variables: unobservable state features that are randomly determined by the environment in a physical setting, but are controllable in a simulator. This can lead to…

Machine Learning · Computer Science 2019-05-28 Supratik Paul , Michael A. Osborne , Shimon Whiteson

Policy gradient methods are powerful reinforcement learning algorithms and have been demonstrated to solve many complex tasks. However, these methods are also data-inefficient, afflicted with high variance gradient estimates, and frequently…

Machine Learning · Computer Science 2019-05-15 Andreas Doerr , Michael Volpp , Marc Toussaint , Sebastian Trimpe , Christian Daniel

Offline reinforcement learning methods hold the promise of learning policies from pre-collected datasets without the need to query the environment for new transitions. This setting is particularly well-suited for continuous control robotic…

Machine Learning · Computer Science 2022-03-18 Xi Chen , Ali Ghadirzadeh , Tianhe Yu , Yuan Gao , Jianhao Wang , Wenzhe Li , Bin Liang , Chelsea Finn , Chongjie Zhang

While reinforcement learning has advanced the alignment of text-to-image (T2I) models, state-of-the-art policy gradient methods are still hampered by training instability and high variance, hindering convergence speed and compromising image…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Jeongjae Lee , Jong Chul Ye

Genetic algorithms have been widely used in many practical optimization problems. Inspired by natural selection, operators, including mutation, crossover and selection, provide effective heuristics for search and black-box optimization.…

Machine Learning · Statistics 2018-03-14 Tanmay Gangwani , Jian Peng

Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajectories, a process crucial for fostering diverse and creative…

Machine Learning · Computer Science 2026-03-13 Aleksei Petrenko , Ben Lipkin , Kevin Chen , Erik Wijmans , Marco Cusumano-Towner , Raja Giryes , Philipp Krähenbühl

Recent success in Deep Reinforcement Learning (DRL) methods has shown that policy optimization with respect to an off-policy distribution via importance sampling is effective for sample reuse. In this paper, we show that the use of…

Machine Learning · Computer Science 2023-02-07 Zichuan Lin , Xiapeng Wu , Mingfei Sun , Deheng Ye , Qiang Fu , Wei Yang , Wei Liu

Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement learning algorithm…

Machine Learning · Computer Science 2025-08-04 David McAllister , Songwei Ge , Brent Yi , Chung Min Kim , Ethan Weber , Hongsuk Choi , Haiwen Feng , Angjoo Kanazawa

Proximal Policy Optimization (PPO) is among the most widely used algorithms in reinforcement learning, which achieves state-of-the-art performance in many challenging problems. The keys to its success are the reliable policy updates through…

Machine Learning · Computer Science 2021-07-02 Mónika Farsang , Luca Szegletes

This work studies reinforcement learning (RL) in the context of multi-period supply chains subject to constraints, e.g., on production and inventory. We introduce Distributional Constrained Policy Optimization (DCPO), a novel approach for…

Machine Learning · Computer Science 2023-02-06 Jaime Sabal Bermúdez , Antonio del Rio Chanona , Calvin Tsay

Post-training with reinforcement learning (RL) has recently shown strong promise for advancing multimodal agents beyond supervised imitation. However, RL remains limited by poor data efficiency, particularly in settings where interaction…

Machine Learning · Computer Science 2026-03-05 Chengxuan Lu , Zhenquan Zhang , Shukuan Wang , Qunzhi Lin , Baigui Sun , Yang Liu