English
Related papers

Related papers: On-Policy RL with Optimal Reward Baseline

200 papers

While Reinforcement Learning (RL) has advanced LLM reasoning, applying it to long-context scenarios is hindered by sparsity of outcome rewards. This limitation fails to penalize ungrounded "lucky guesses," leaving the critical process of…

Artificial Intelligence · Computer Science 2026-04-21 Xin Guan , Zijian Li , Shen Huang , Pengjun Xie , Jingren Zhou , Jiuxin Cao

Contrastive reinforcement learning (CRL) learns goal-conditioned Q-values through a contrastive objective over state-action and goal representations, removing the need for hand-crafted reward functions. Despite impressive success in…

Group Relative Policy Optimization (GRPO) has been a key driver of recent progress in reinforcement learning with verifiable rewards (RLVR) for large language models, but it is typically trained in a low-staleness, near-on-policy regime…

Machine Learning · Computer Science 2026-05-19 Minghao Tian , Yunfei Xie , Chen Wei

We propose Process-Aware Policy Optimization (PAPO), a method that integrates process-level evaluation into Group Relative Policy Optimization (GRPO) through decoupled advantage normalization, to address two limitations of existing reward…

Artificial Intelligence · Computer Science 2026-04-06 Zelin Tan , Zhouliang Yu , Bohan Lin , Zijie Geng , Hejia Geng , Yudong Zhang , Mulei Zhang , Yang Chen , Shuyue Hu , Zhenfei Yin , Chen Zhang , Lei Bai

Score-function based methods for policy learning, such as REINFORCE and PPO, have delivered strong results in game-playing and robotics, yet their high variance often undermines training stability. Using pathwise policy gradients, i.e.…

Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While…

Machine Learning · Computer Science 2018-12-27 Chen Tessler , Daniel J. Mankowitz , Shie Mannor

Reinforcement learning has become a central paradigm for improving LLM reasoning. However, existing methods use a single policy to produce both inference responses and training optimization trajectories. The objective conflict between…

Machine Learning · Computer Science 2026-01-26 Jingchu Wang , Bingbing Xu , Yige Yuan , Bin Xie , Xiaoqian Sun , Huawei Shen

RL-based post-training of language models is almost exclusively done using on-policy methods such as PPO. These methods cannot learn from arbitrary sequences such as those produced earlier in training, in earlier runs, by human experts or…

Machine Learning · Computer Science 2025-03-10 Taco Cohen , David W. Zhang , Kunhao Zheng , Yunhao Tang , Remi Munos , Gabriel Synnaeve

Reward shaping is critical in reinforcement learning (RL), particularly for complex tasks where sparse rewards can hinder learning. However, choosing effective shaping rewards from a set of reward functions in a computationally efficient…

Machine Learning · Computer Science 2025-02-26 Chen Bo Calvin Zhang , Zhang-Wei Hong , Aldo Pacchiano , Pulkit Agrawal

Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of…

Machine Learning · Computer Science 2025-10-14 Mingyang Lyu , Yinqian Sun , Erliang Lin , Huangrui Li , Ruolin Chen , Feifei Zhao , Yi Zeng

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tasks. However,…

Machine Learning · Computer Science 2025-07-17 Ziru Liu , Cheng Gong , Xinyu Fu , Yaofang Liu , Ran Chen , Shoubo Hu , Suiyun Zhang , Rui Liu , Qingfu Zhang , Dandan Tu

Reinforcement learning (RL) is a powerful machine learning technique that enables an intelligent agent to learn an optimal policy that maximizes the cumulative rewards in sequential decision making. Most of methods in the existing…

Machine Learning · Statistics 2023-01-06 Chengchun Shi , Zhengling Qi , Jianing Wang , Fan Zhou

Recent advances in large reasoning models have leveraged reinforcement learning with verifiable rewards (RLVR) to improve reasoning capabilities. However, scaling these methods typically requires extensive rollout computation and large…

Machine Learning · Computer Science 2025-09-03 Xinyu Tang , Zhenduo Zhang , Yurou Liu , Wayne Xin Zhao , Zujie Wen , Zhiqiang Zhang , Jun Zhou

Standard reinforcement learning from human feedback (RLHF) trains a reward model on pairwise preference data and then uses it for policy optimization. However, while reward models are optimized to capture relative preferences, existing…

Machine Learning · Computer Science 2026-02-05 Kyuseong Choi , Dwaipayan Saha , Woojeong Kim , Anish Agarwal , Raaz Dwivedi

Classical reinforcement learning (RL) aims to optimize the expected cumulative rewards. In this work, we consider the RL setting where the goal is to optimize the quantile of the cumulative rewards. We parameterize the policy controlling…

Machine Learning · Computer Science 2022-02-17 Jinyang Jiang , Jiaqiao Hu , Yijie Peng

Reinforcement learning (RL) has emerged as a promising paradigm for inducing explicit reasoning behaviors in large language and vision-language models. However, reasoning-oriented RL post-training remains fundamentally challenging due to…

Artificial Intelligence · Computer Science 2026-05-13 Fan Yang , Rui Meng , Trudi Di Qi , Ali Ezzati , Yuxin Wen

This paper endeavors to augment the robustness of offline reinforcement learning (RL) in scenarios laden with heavy-tailed rewards, a prevalent circumstance in real-world applications. We propose two algorithmic frameworks, ROAM and ROOM,…

Machine Learning · Computer Science 2024-04-02 Jin Zhu , Runzhe Wan , Zhengling Qi , Shikai Luo , Chengchun Shi

Group Relative Policy Optimization(GRPO) has become a cornerstone of modern reinforcement learning alignment, prized for its efficacy in foregoing an explicit value-critic by leveraging reward normalization across sampled trajectory…

Computation and Language · Computer Science 2026-05-29 Redacted by arXiv

We deploy large language models (LLMs) as business development (BD) agents for persuasive price negotiation in online travel agencies (OTAs). The agent must follow a multi-stage Standard Operating Procedure (SOP) and strict guardrails (no…

Computation and Language · Computer Science 2026-04-30 Xia Zeng , Yihan Chen , Luhui Liu , Chao Luo , Ye Chen , Zhuoran Zhuang

Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for…

Machine Learning · Computer Science 2026-02-04 Ruiyi Ding , Yongxuan Lv , Xianhui Meng , Jiahe Song , Chao Wang , Chen Jiang , Yuan Cheng