English
Related papers

Related papers: Flexible Entropy Control in RLVR with a Gradient-P…

200 papers

The policy gradient method enjoys the simplicity of the objective where the agent optimizes the cumulative reward directly. Moreover, in the continuous action domain, parameterized distribution of action distribution allows easy control of…

Machine Learning · Computer Science 2022-12-16 Md Masudur Rahman , Yexiang Xue

Deep Reinforcement Learning (Deep RL) has had incredible achievements on high dimensional problems, yet its learning process remains unstable even on the simplest tasks. Deep RL uses neural networks as function approximators. These neural…

Machine Learning · Computer Science 2022-10-18 Riccardo Della Vecchia , Alena Shilova , Philippe Preux , Riad Akrour

Despite its popularity in the reinforcement learning community, a provably convergent policy gradient method for continuous space-time control problems with nonlinear state dynamics has been elusive. This paper proposes proximal gradient…

Optimization and Control · Mathematics 2022-12-27 Christoph Reisinger , Wolfgang Stockinger , Yufei Zhang

Reinforcement Learning from Verifiable Rewards (RLVR) trains large language models (LLMs) from sampled trajectories, making decoding strategy a core component of learning rather than a purely inference-time choice. Sampling temperature…

Machine Learning · Computer Science 2026-02-16 Yixiao Zhou , Yang Li , Dongzhou Cheng , Hehe Fan , Yu Cheng

For RL algorithms, appropriate entropy control is crucial to their effectiveness. To control the policy entropy, a commonly used method is entropy regularization, which is adopted in various popular RL algorithms including PPO, SAC and A3C.…

Machine Learning · Computer Science 2026-02-06 Han Shen

Reinforcement learning from verifiable rewards (RLVR) suffers from sparse outcome signals, creating severe exploration bottlenecks on complex reasoning tasks. Recent on-policy self-distillation methods attempt to address this by utilizing…

Machine Learning · Computer Science 2026-05-20 Yang Li , Erik Nijkamp , Semih Yavuz , Shafiq Joty

Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustness is important. Despite the impressive results of deep reinforcement learning in complex control tasks, it is prone to capturing…

Machine Learning · Computer Science 2025-05-09 Bang You , Chenxu Wang , Huaping Liu

Maximum entropy reinforcement learning integrates exploration into policy learning by providing additional intrinsic rewards proportional to the entropy of some distribution. In this paper, we propose a novel approach in which the intrinsic…

Machine Learning · Computer Science 2025-09-30 Adrien Bolland , Gaspard Lambrechts , Damien Ernst

While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi-criteria supervision (e.g., perceptual details, reasoning…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Ya-Qi Yu , Hao Wang , Fangyu Hong , Xiangyang Qu , Gaojie Wu , Qiaoyu Luo , Nuo Xu , Huixin Wang , Wuheng Xu , Yongxin Liao , Zihao Chen , Haonan Li , Ziming Li , Dezhi Peng , Minghui Liao , Jihao Wu , Haoyu Ren , Dandan Tu

The success of Deepseek-R1 has drawn the LLM community's attention to reinforcement learning (RL) methods like GRPO. However, such rule-based 0/1 outcome reward methods lack the capability to regulate the intermediate reasoning processes…

Artificial Intelligence · Computer Science 2025-05-26 Muzhi Dai , Shixuan Liu , Qingyi Si

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Computation and Language · Computer Science 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

Reinforcement Learning with Verifiable Rewards has recently advanced the capabilities of Large Language Models in complex reasoning tasks by providing explicit rule-based supervision. Among RLVR methods, GRPO and its variants have achieved…

Machine Learning · Computer Science 2026-03-11 Zepeng Zhai , Meilin Chen , Jiaxuan Zhao , Junlang Qian , Lei Shen , Yuan Lu

In Vision-Language Models (VLMs), processing a massive number of visual tokens incurs prohibitive computational overhead. While recent training-aware pruning methods attempt to selectively discard redundant tokens, they largely rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Mingzhe Huang , Weijun Wang , Xin Ding , Liang Mi , Hao Wen , Yuanchun Li , Lichen Pang , Shansong Yang , Yunxin Liu , Ting Cao

This work uses the entropy-regularised relaxed stochastic control perspective as a principled framework for designing reinforcement learning (RL) algorithms. Herein agent interacts with the environment by generating noisy controls…

Machine Learning · Computer Science 2023-09-18 Lukasz Szpruch , Tanut Treetanthiploet , Yufei Zhang

Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation remains profoundly challenging due to the lack of definitive rewards. Current…

Computation and Language · Computer Science 2026-05-29 Xin Guan , Xiaomeng Hu , Shen Huang , Zhenyi Wang , Bo Zhang , Zijian Li , Pengjun Xie , Bo Liu , Jiuxin Cao

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capacity of Large Language Models (LLMs). However, RLVR solely relies on final answers as outcome rewards, neglecting the correctness of…

Machine Learning · Computer Science 2026-03-12 Sijia Cui , Pengyu Cheng , Jiajun Song , Yongbo Gai , Guojun Zhang , Zhechao Yu , Jianhe Lin , Xiaoxi Jiang , Guanjun Jiang

In recent years, fully differentiable rigid body physics simulators have been developed, which can be used to simulate a wide range of robotic systems. In the context of reinforcement learning for control, these simulators theoretically…

Machine Learning · Computer Science 2022-03-08 Sean Gillen , Katie Byl

Privacy-preserving training on sensitive data commonly relies on differentially private stochastic optimization with gradient clipping and Gaussian noise. The clipping threshold is a critical control knob: if set too small, systematic…

Machine Learning · Computer Science 2026-02-12 Mohammad Partohaghighi , Roummel Marcia , Bruce J. West , YangQuan Chen

Large reasoning models (LRMs) aim to solve diverse and complex problems through structured reasoning. Recent advances in group-based policy optimization methods have shown promise in enabling stable advantage estimation without reliance on…

Machine Learning · Computer Science 2026-01-29 Zhizheng Jiang , Kang Zhao , Weikai Xu , Xinkui Lin , Wei Liu , Jian Luan , Shuo Shang , Peng Han

Reinforcement Learning with Verifiable Rewards (RLVR) improves reasoning in large language models but treats all correct solutions equally, potentially reinforcing flawed traces that get correct answers by chance. We observe that better…

Machine Learning · Computer Science 2026-03-11 Tiehua Mei , Minxuan Lv , Leiyu Pan , Zhenpeng Su , Hongru Hou , Hengrui Chen , Ao Xu , Deqing Yang