English
Related papers

Related papers: Stabilizing Long-term Multi-turn Reinforcement Lea…

200 papers

Reinforcement Learning (RL) is a promising approach for achieving autonomous driving due to robust decision-making capabilities. RL learns a driving policy through trial and error in traffic scenarios, guided by a reward function that…

Leveraging the priors of 2D diffusion models for 3D editing has emerged as a promising paradigm. However, maintaining multi-view consistency in edited results remains challenging, and the extreme scarcity of 3D-consistent editing paired…

Computer Vision and Pattern Recognition · Computer Science 2026-03-04 Jiyuan Wang , Chunyu Lin , Lei Sun , Zhi Cao , Yuyang Yin , Lang Nie , Zhenlong Yuan , Xiangxiang Chu , Yunchao Wei , Kang Liao , Guosheng Lin

Long-form generation has become a critical and challenging application for Large Language Models (LLMs). Existing studies are limited by their reliance on scarce, high-quality long-form response data and their focus on coarse-grained,…

Computation and Language · Computer Science 2026-01-01 Jianghao Chen , Wei Sun , Qixiang Yin , Zhixing Tan , Jiajun Zhang

Fine-grained visual reasoning remains a core challenge for multimodal large language models (MLLMs). The recently introduced ReasonMap highlights this gap by showing that even advanced MLLMs struggle with spatial reasoning in structured and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Sicheng Feng , Kaiwen Tuo , Song Wang , Lingdong Kong , Jianke Zhu , Huan Wang

Goal-Conditioned Reinforcement Learning (RL) problems often have access to sparse rewards where the agent receives a reward signal only when it has achieved the goal, making policy optimization a difficult problem. Several works augment…

Machine Learning · Computer Science 2023-10-11 Siddhant Agarwal , Ishan Durugkar , Peter Stone , Amy Zhang

Reinforcement Learning with Verifiable Rewards (RLVR) improves final-answer accuracy on reasoning tasks, but it does not reliably improve reasoning quality. Because outcome rewards only assess final answers, they also reward spurious…

Machine Learning · Computer Science 2026-05-19 Chenlu Ye , Zhou Yu , Ziji Zhang , Hao Chen , Narayanan Sadagopan , Jing Huang , Tong Zhang , Anurag Beniwal

Reward function is essential in reinforcement learning (RL), serving as the guiding signal to incentivize agents to solve given tasks, however, is also notoriously difficult to design. In many cases, only imperfect rewards are available,…

Machine Learning · Computer Science 2023-02-06 Jianxiong Li , Xiao Hu , Haoran Xu , Jingjing Liu , Xianyuan Zhan , Qing-Shan Jia , Ya-Qin Zhang

In constrained reinforcement learning (RL), a learning agent seeks to not only optimize the overall reward but also satisfy the additional safety, diversity, or budget constraints. Consequently, existing constrained RL solutions require…

Machine Learning · Computer Science 2021-07-13 Sobhan Miryoosefi , Chi Jin

Existing reinforcement learning (RL) methods struggle with long-horizon robotic manipulation tasks, particularly those involving sparse rewards. While action chunking is a promising paradigm for robotic manipulation, using RL to directly…

Robotics · Computer Science 2026-03-02 Jiarui Yang , Bin Zhu , Jingjing Chen , Yu-Gang Jiang

Multi-turn reinforcement learning (RL) for multi-modal agents built upon vision-language models (VLMs) is hampered by sparse rewards and long-horizon credit assignment. Recent methods densify the reward by querying a teacher that provides…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Tong Wei , Yijun Yang , Changhao Zhang , Junliang Xing , Yuanchun Shi , Zongqing Lu , Deheng Ye

Reinforcement Learning with Verifiable Rewards (RLVR) elicits long chain-of-thought reasoning in large language models (LLMs), but outcome-based rewards lead to coarse-grained advantage estimation. While existing approaches improve RLVR via…

Computation and Language · Computer Science 2026-01-08 Fei Wu , Zhenrong Zhang , Qikai Chang , Jianshu Zhang , Quan Liu , Jun Du

Reinforcement Learning (RL) has the potential to enable robots to learn from their own actions in the real world. Unfortunately, RL can be prohibitively expensive, in terms of on-robot runtime, due to inefficient exploration when learning…

In recent years, a variety of tasks have been accomplished by deep reinforcement learning (DRL). However, when applying DRL to tasks in a real-world environment, designing an appropriate reward is difficult. Rewards obtained via actual…

Machine Learning · Computer Science 2023-10-04 Kanata Suzuki , Tetsuya Ogata

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, yet traditional single-round retrieval struggles with complex multi-step reasoning. Agentic RAG addresses this by enabling LLMs…

Computation and Language · Computer Science 2026-02-27 Tianle Xia , Ming Xu , Lingxiang Hu , Yiding Sun , Wenwei Li , Linfang Shang , Liqun Liu , Peng Shu , Huan Yu , Jie Jiang

Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of large language models (LLMs) on mathematics and programming tasks, but standard approaches that optimize single-attempt accuracy can inadvertently…

Machine Learning · Computer Science 2026-02-27 Devan Shah , Owen Yang , Daniel Yang , Chongyi Zheng , Benjamin Eysenbach

Multi-agent hierarchical reinforcement learning (MAHRL) has been studied as an effective means to solve intelligent decision problems in complex and large-scale environments. However, most current MAHRL algorithms follow the traditional way…

Artificial Intelligence · Computer Science 2024-11-05 Chanjuan Liu , Jinmiao Cong , Bingcai Chen , Yaochu Jin , Enqiang Zhu

This paper develops LongNav-R1, an end-to-end multi-turn reinforcement learning (RL) framework designed to optimize Visual-Language-Action (VLA) models for long-horizon navigation. Unlike existing single-turn paradigm, LongNav-R1…

Robotics · Computer Science 2026-02-16 Yue Hu , Avery Xi , Qixin Xiao , Seth Isaacson , Henry X. Liu , Ram Vasudevan , Maani Ghaffari

Reinforcement learning (RL) algorithms have been successfully applied to control tasks associated with unmanned aerial vehicles and robotics. In recent years, safe RL has been proposed to allow the safe execution of RL algorithms in…

Machine Learning · Computer Science 2025-02-25 Austin Coursey , Marcos Quinones-Grueiro , Gautam Biswas

Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal Large Language Models. However, extending this success to open-source multimodal…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Wenbo Hu , Xin Chen , Yan Gao-Tian , Yihe Deng , Nanyun Peng , Kai-Wei Chang

Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactive tasks. However, in partially observable environments, incomplete observations cause…

Computation and Language · Computer Science 2026-05-20 Wenjie Tang , Minne Li , Sijie Huang , Liquan Xiao , Yuan Zhou
‹ Prev 1 8 9 10 Next ›