English
Related papers

Related papers: Beyond Trajectory Rewards: Step-level Credit Assig…

200 papers

Unsupervised goal-conditioned reinforcement learning (GCRL) is a promising paradigm for developing diverse robotic skills without external supervision. However, existing unsupervised GCRL methods often struggle to cover a wide range of…

Machine Learning · Computer Science 2024-12-10 Junik Bae , Kwanyoung Park , Youngwoon Lee

Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…

Machine Learning · Computer Science 2024-02-08 Guojian Wang , Faguo Wu , Xiao Zhang , Jianxiang Liu

Goal-conditioned hierarchical reinforcement learning (GCHRL) provides a promising approach to solving long-horizon tasks. Recently, its success has been extended to more general settings by concurrently learning hierarchical policies and…

Machine Learning · Computer Science 2022-03-08 Siyuan Li , Jin Zhang , Jianhao Wang , Yang Yu , Chongjie Zhang

Large Language Models (LLMs) have demonstrated remarkable capabilities, enabling language agents to excel at single-turn tasks. However, their application to complex, multi-step, and long-horizon tasks remains challenging. While…

Machine Learning · Computer Science 2025-10-24 Jiazheng Li , Yawei Wang , David Yan , Yijun Tian , Zhichao Xu , Huan Song , Panpan Xu , Lin Lee Cheong

Reinforcement learning (RL) holds significant promise for training LLM agents to handle complex, goal-oriented tasks that require multi-step interactions with external environments. However, a critical challenge when applying RL to these…

Computation and Language · Computer Science 2025-05-28 Hanlin Wang , Chak Tou Leong , Jiashuo Wang , Jian Wang , Wenjie Li

Retrieval-augmented generation (RAG) and its graph-based extensions (GraphRAG) are effective paradigms for improving large language model (LLM) reasoning by grounding generation in external knowledge. However, most existing RAG and GraphRAG…

Information Retrieval · Computer Science 2026-04-14 Dongzhe Fan , Zheyi Xue , Siyuan Liu , Qiaoyu Tan

Agentic RAG is a powerful technique for incorporating external information that LLMs lack, enabling better problem solving and question answering. However, suboptimal search behaviors exist widely, such as over-search (retrieving…

Computation and Language · Computer Science 2026-04-14 Peilin Wu , Mian Zhang , Kun Wan , Wentian Zhao , Kaiyu He , Xinya Du , Zhiyu Chen

Reinforcement Learning (RL) has achieved remarkable success in various domains, yet it often relies on carefully designed programmatic reward functions to guide agent behavior. Designing such reward functions can be challenging and may not…

Machine Learning · Computer Science 2026-04-06 Qi Wang , Mian Wu , Yuyang Zhang , Mingqi Yuan , Wenyao Zhang , Haoxiang You , Yunbo Wang , Xin Jin , Xiaokang Yang , Wenjun Zeng

Despite rapid development, large language models (LLMs) still encounter challenges in multi-turn decision-making tasks (i.e., agent tasks) like web shopping and browser navigation, which require making a sequence of intelligent decisions…

Computation and Language · Computer Science 2025-11-12 Zhiheng Xi , Chenyang Liao , Guanyu Li , Yajie Yang , Wenxiang Chen , Zhihao Zhang , Binghai Wang , Senjie Jin , Yuhao Zhou , Jian Guan , Wei Wu , Tao Ji , Tao Gui , Qi Zhang , Xuanjing Huang

In reinforcement learning, we typically aim to optimize the expected value of the sum of rewards an agent collects over a trajectory. However, if the process generating these rewards is non-ergodic, the expected value, i.e., the average…

Stepwise model routing improves the efficiency of Large Reasoning Models (LRMs) by assigning each reasoning step to a suitable model. Recent methods formulate routing as a sequential decision process and train the router with reinforcement…

Artificial Intelligence · Computer Science 2026-05-29 Shenghao Ye , Yu Guo , Zhengheng Li , Shuangwu Chen , Jian Yang

Recently, Group Relative Policy Optimization (GRPO) has shown promising potential for aligning text-to-image (T2I) models, yet existing GRPO-based methods suffer from two critical limitations. (1) \textit{Shared credit assignment}:…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Qiang Lyu , Zicong Chen , Chongxiao Wang , Haolin Shi , Shibo Gao , Ran Piao , Youwei Zeng , Jianlou Si , Fei Ding , Jing Li , Chun Pong Lau , Weiqiang Wang

In recent years, deep Reinforcement Learning (RL) has been successful in various combinatorial search domains, such as two-player games and scientific discovery. However, directly applying deep RL in planning domains is still challenging.…

Artificial Intelligence · Computer Science 2022-09-21 Dieqiao Feng , Carla P. Gomes , Bart Selman

Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs) through the dynamic integration of external knowledge. To further improve RAG's flexibility, Agentic RAG…

Information Retrieval · Computer Science 2026-05-19 Hao Sun , Zile Qiao , Bo Wang , Guoxin Chen , Yingyan Hou , Yong Jiang , Pengjun Xie , Fei Huang , Yan Zhang

While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited. Most existing methods concentrate on designing effective reward models (RMs) to advance…

Machine Learning · Computer Science 2026-03-20 Zhicong Lu , Zichuan Lin , Wei Jia , Changyuan Tian , Deheng Ye , Peiguang Li , Li Jin , Nayu Liu , Guangluan Xu , Wei Feng

In this paper, we study the application of DRL algorithms in the context of local navigation problems, in which a robot moves towards a goal location in unknown and cluttered workspaces equipped only with limited-range exteroceptive…

Robotics · Computer Science 2025-06-17 Victor R. F. Miranda , Armando A. Neto , Gustavo M. Freitas , Leonardo A. Mozelli

The standard feedback model of reinforcement learning requires revealing the reward of every visited state-action pair. However, in practice, it is often the case that such frequent feedback is not available. In this work, we take a first…

Machine Learning · Computer Science 2021-03-08 Yonathan Efroni , Nadav Merlis , Shie Mannor

Procedural activities are sequences of key-steps aimed at achieving specific goals. They are crucial to build intelligent agents able to assist users effectively. In this context, task graphs have emerged as a human-understandable…

Computer Vision and Pattern Recognition · Computer Science 2025-01-10 Luigi Seminara , Giovanni Maria Farinella , Antonino Furnari

Multi-turn interaction remains challenging for online reinforcement learning. A common solution is trajectory-level optimization, which treats each trajectory as a single training sample. However, this approach can be inefficient and yield…

Artificial Intelligence · Computer Science 2025-11-18 Yuhan Chen , Yuxuan Liu , Long Zhang , Pengzhi Gao , Jian Luan , Wei Liu

Large language model (LLM)-based agents are increasingly trained with reinforcement learning (RL) to enhance their ability to interact with external environments through tool use, particularly in search-based settings that require…

Computation and Language · Computer Science 2026-03-25 Guoqing Wang , Sunhao Dai , Guangze Ye , Zeyu Gan , Wei Yao , Yong Deng , Xiaofeng Wu , Zhenzhe Ying