English
Related papers

Related papers: DiPO: Disentangled Perplexity Policy Optimization …

200 papers

Reinforcement learning with verifiable rewards (RLVR) has substantially enhanced the reasoning capabilities of multimodal large language models (MLLMs). However, existing RLVR approaches typically rely on outcome-driven optimization that…

Artificial Intelligence · Computer Science 2026-04-10 Ziqi Miao , Haonan Jia , Lijun Li , Chen Qian , Yuan Xiong , Wenting Yan , Jing Shao

Large Vision-Language Models (LVLMs) have recently advanced robotic manipulation by leveraging vision for scene perception and language for instruction following. However, existing methods rely heavily on costly human-annotated training…

Exploration remains a critical challenge in online reinforcement learning, as an agent must effectively explore unknown environments to achieve high returns. Currently, the main exploration algorithms are primarily count-based methods and…

Machine Learning · Computer Science 2025-05-19 Zhirui Fang , Kai Yang , Jian Tao , Jiafei Lyu , Lusong Li , Li Shen , Xiu Li

Reinforcement learning (RL) has increasingly become a pivotal technique in the post-training of large language models (LLMs). The effective exploration of the output space is essential for the success of RL. We observe that for complex…

Machine Learning · Computer Science 2025-07-08 Shihan Dou , Muling Wu , Jingwen Xu , Rui Zheng , Tao Gui , Qi Zhang , Xuanjing Huang

Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and scale performance with test-time compute. In this paper, we present a framework for…

Artificial Intelligence · Computer Science 2026-05-06 Ifdita Hasan Orney , Jubayer Ibn Hamid , Shreya S Ramanujam , Shirley Wu , Hengyuan Hu , Noah Goodman , Dorsa Sadigh , Chelsea Finn

This paper bridges reinforcement learning (RL) and risk-sensitive stochastic control by introducing a tractable exploration mechanism for policy search in risk-sensitive portfolio management, with known and unknown model parameters, that…

Portfolio Management · Quantitative Finance 2026-03-03 Sebastien Lleo , Wolfgang Runggaldier

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising framework for improving reasoning abilities in Large Language Models (LLMs). However, policy optimized with binary verification prone to overlook…

Machine Learning · Computer Science 2025-10-14 Jinghao Zhang , Naishan Zheng , Ruilin Li , Dongzhou Cheng , Zheming Liang , Feng Zhao , Jiaqi Wang

Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes. While recent alignment techniques such as RLHF and DPO have mitigated some of these issues, they remain…

Computation and Language · Computer Science 2025-11-11 Deng Yixuan , Ji Xiaoqiang

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

Navigating and understanding complex and unknown environments autonomously demands more than just basic perception and movement from embodied agents. Truly effective exploration requires agents to possess higher-level cognitive abilities,…

Artificial Intelligence · Computer Science 2025-09-12 Abdel Hakim Drid , Vincenzo Suriani , Daniele Nardi , Abderrezzak Debilou

Recent work shows that preference alignment objectives can be interpreted as divergence estimators between aligned (preferred) & unaligned (less-preferred) distributions, yielding a principled recipe for designing alignment losses. However,…

Machine Learning · Computer Science 2026-05-12 Rajdeep Haldar , Lantao Mei , Guang Lin , Yue Xing , Qifan Song

State-of-the-art reinforcement learning (RL) algorithms typically use random sampling (e.g., $\epsilon$-greedy) for exploration, but this method fails on hard exploration tasks like Montezuma's Revenge. To address the challenge of…

Machine Learning · Computer Science 2022-11-21 Eric Chen , Zhang-Wei Hong , Joni Pajarinen , Pulkit Agrawal

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy…

Computation and Language · Computer Science 2024-03-29 Hao Lang , Fei Huang , Yongbin Li

Recent advancements have shown that reinforcement learning (RL) can substantially improve the reasoning abilities of large language models (LLMs). The effectiveness of such RL training, however, depends critically on the exploration space…

Computation and Language · Computer Science 2026-03-17 Haoyuan Wu , Hai Wang , Jiajia Wu , Jinxiang Ou , Keyao Wang , Weile Chen , Zihao Zheng , Bei Yu

Reinforcement learning with verifiable rewards (RLVR), which typically adopts Pass@1 as the reward, has faced the issues in balancing exploration and exploitation, causing policies to prefer conservative actions, converging to a local…

Machine Learning · Computer Science 2025-08-15 Zhipeng Chen , Xiaobo Qin , Youbin Wu , Yue Ling , Qinghao Ye , Wayne Xin Zhao , Guang Shi

We consider deep deterministic policy gradient (DDPG) in the context of reinforcement learning with sparse rewards. To enhance exploration, we introduce a search procedure, \emph{${\epsilon}{t}$-greedy}, which generates exploratory options…

Machine Learning · Computer Science 2026-02-18 Ehsan Futuhi , Shayan Karimi , Chao Gao , Martin Müller

Learning to rank (LTR) plays a crucial role in various Information Retrieval (IR) tasks. Although supervised LTR methods based on fine-grained relevance labels (e.g., document-level annotations) have achieved significant success, their…

Information Retrieval · Computer Science 2025-08-21 Yiteng Tu , Zhichao Xu , Tao Yang , Weihang Su , Yujia Zhou , Yiqun Liu , Fen Lin , Qin Liu , Qingyao Ai

Process reward models (PRMs) provide fine-grained supervision for reasoning, but reliable PRMs often require step annotations or heavy verification pipelines, making them costly to scale and refresh during online RL. Implicit PRMs reduce…

Computation and Language · Computer Science 2026-05-29 Shiping Gao , Hongzhan Chen , Xiaojun Quan , Qifan Wang , Lifu Huang

Reinforcement Learning with Verifiable Rewards (RLVR) has propelled Large Language Models in complex reasoning, yet its scalability is often hindered by a training bottleneck where performance plateaus as policy entropy collapses, signaling…

Machine Learning · Computer Science 2025-11-10 Guanhua Huang , Tingqiang Xu , Mingze Wang , Qi Yi , Xue Gong , Siheng Li , Ruibin Xiong , Kejiao Li , Yuhao Jiang , Bo Zhou

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