English
Related papers

Related papers: Complexity-Regularized Proximal Policy Optimizatio…

200 papers

Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms in contemporary reinforcement learning. This class of methods is often applied in conjunction with entropy regularization -- an algorithmic…

Machine Learning · Statistics 2022-09-13 Shicong Cen , Chen Cheng , Yuxin Chen , Yuting Wei , Yuejie Chi

Process reward models (PRMs) allow for fine-grained credit assignment in reinforcement learning (RL), and seemingly contrast with outcome reward models (ORMs), which assign a single reward to an entire trajectory. However, we provide…

Machine Learning · Computer Science 2026-05-29 Michael Sullivan , Alexander Koller

Provably efficient Model-Based Reinforcement Learning (MBRL) based on optimism or posterior sampling (PSRL) is ensured to attain the global optimality asymptotically by introducing the complexity measure of the model. However, the…

Machine Learning · Computer Science 2022-09-19 Shenao Zhang

In this paper, we propose a new algorithm PPG (Proximal Policy Gradient), which is close to both VPG (vanilla policy gradient) and PPO (proximal policy optimization). The PPG objective is a partial variation of the VPG objective and the…

Machine Learning · Computer Science 2020-10-21 Ju-Seung Byun , Byungmoon Kim , Huamin Wang

In this work, we show that discretizing action space for continuous control is a simple yet powerful technique for on-policy optimization. The explosion in the number of discrete actions can be efficiently addressed by a policy with…

Machine Learning · Computer Science 2020-03-23 Yunhao Tang , Shipra Agrawal

Recent theory suggests that reward-model-first methods can be more sample-efficient than direct policy fitting when the reward function is statistically simpler than the induced policy. We propose DDO-RM, a finite-candidate…

Machine Learning · Statistics 2026-05-01 Tiantian Zhang , Jierui Zuo , Michael Chen , Wenping Wang

Safe reinforcement learning (safe RL) aims to respect safety requirements while optimizing long-term performance. In many practical applications, however, the problem involves an infinite number of constraints, known as semi-infinite safe…

Machine Learning · Computer Science 2025-11-07 Jiaming Zhang , Yujie Yang , Haoning Wang , Liping Zhang , Shengbo Eben Li

The increasing capabilities of large language models (LLMs) raise opportunities for artificial general intelligence but concurrently amplify safety concerns, such as potential misuse of AI systems, necessitating effective AI alignment.…

Machine Learning · Computer Science 2023-09-29 Chaoqi Wang , Yibo Jiang , Chenghao Yang , Han Liu , Yuxin Chen

Reinforcement learning (RL) has become a key driver of language model reasoning. Among RL algorithms, Group Relative Policy Optimization (GRPO) is the de facto standard, avoiding the need for a critic by using per-prompt baselines and…

Machine Learning · Computer Science 2026-02-02 Cheng Ge , Caitlyn Heqi Yin , Hao Liang , Jiawei Zhang

Constrained reinforcement learning has achieved promising progress in safety-critical fields where both rewards and constraints are considered. However, constrained reinforcement learning methods face challenges in striking the right…

Machine Learning · Computer Science 2024-10-29 Jianmina Ma , Jingtian Ji , Yue Gao

In the classical Reinforcement Learning from Human Feedback (RLHF) framework, Proximal Policy Optimization (PPO) is employed to learn from sparse, sentence-level rewards -- a challenging scenario in traditional deep reinforcement learning.…

Machine Learning · Computer Science 2025-05-22 Han Zhong , Zikang Shan , Guhao Feng , Wei Xiong , Xinle Cheng , Li Zhao , Di He , Jiang Bian , Liwei Wang

While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications, including the fine-tuning of generative models.…

Recent successful deep reinforcement learning algorithms, such as Trust Region Policy Optimization (TRPO) or Proximal Policy Optimization (PPO), are fundamentally variations of conservative policy iteration (CPI). These algorithms iterate…

Machine Learning · Computer Science 2020-01-27 Erinc Merdivan , Sten Hanke , Matthieu Geist

The key to building trustworthy large language models (LLMs) lies in endowing them with inherent uncertainty expression capabilities, thereby mitigating overconfident errors in high-stakes applications. However, existing RL paradigms such…

Artificial Intelligence · Computer Science 2026-05-27 Xianzhou Zeng , Jing Huang , Chunmei Xie , Gongrui Nan , Siye Chen , Mengyu Lu , Weiqi Xiong , Qixuan Zhou , Junhao Zhang , Qiang Zhu , Yadong Li , Xingzhong Xu

The advantage function is a central concept in RL that helps reduce variance in policy gradient estimates. For language modeling, Group Relative Policy Optimization (GRPO) was proposed to use the within-group sample mean as a baseline for…

Machine Learning · Computer Science 2026-04-23 Hu Wang , Congbo Ma , Ian Reid , Mohammad Yaqub

Proximal Policy Optimization (PPO) is among the most widely used deep reinforcement learning algorithms, yet its theoretical foundations remain incomplete. Most importantly, convergence and understanding of fundamental PPO advantages remain…

Machine Learning · Computer Science 2026-02-04 Leif Doering , Daniel Schmidt , Moritz Melcher , Sebastian Kassing , Benedikt Wille , Tilman Aach , Simon Weissmann

Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex reasoning tasks due to the difficulty of assigning correct…

Computation and Language · Computer Science 2025-07-08 Archiki Prasad , Weizhe Yuan , Richard Yuanzhe Pang , Jing Xu , Maryam Fazel-Zarandi , Mohit Bansal , Sainbayar Sukhbaatar , Jason Weston , Jane Yu

Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularly for nuanced tasks like emotion control. The policy model…

Sound · Computer Science 2026-02-17 Cong Wang , Changfeng Gao , Yang Xiang , Zhihao Du , Keyu An , Han Zhao , Qian Chen , Xiangang Li , Yingming Gao , Ya Li

Aligning large language models with pointwise absolute rewards has so far required online, on-policy algorithms such as PPO and GRPO. In contrast, simpler methods that can leverage offline or off-policy data, such as DPO and REBEL, are…

Machine Learning · Computer Science 2025-12-02 Simon Matrenok , Skander Moalla , Caglar Gulcehre

In this paper, we introduce \emph{refined Direct Preference Optimization} (rDPO), a method for improving the behavioral alignment of Large Language Models (LLMs) without the need for human-annotated data. The method involves creating…

Computation and Language · Computer Science 2024-02-14 Víctor Gallego