English
Related papers

Related papers: ToolRLA: Multiplicative Reward Decomposition for T…

200 papers

(This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.) To improve the efficiency of deep reinforcement learning (DRL)-based…

Artificial Intelligence · Computer Science 2021-05-25 Gang Peng , Jin Yang , Xinde Lia , Mohammad Omar Khyam

Reinforcement learning (RL) relies heavily on exploration to learn from its environment and maximize observed rewards. Therefore, it is essential to design a reward function that guarantees optimal learning from the received experience.…

Artificial Intelligence · Computer Science 2022-06-20 Ingy ElSayed-Aly , Lu Feng

Reinforcement learning can train LLM agents from sparse task rewards, but long-horizon credit assignment remains challenging: a single success-or-failure signal must be distributed across many actions. Existing methods rely on…

Artificial Intelligence · Computer Science 2026-05-20 Xiaozhe Li , Tianyi Lyu , Yang Li , Yichuan Ma , Peiji Li , Linyang Li , Qipeng Guo , Dahua Lin , Kai Chen

Reinforcement learning (RL) is pivotal for enhancing the reasoning capabilities of diffusion large language models (dLLMs). However, existing dLLM policy optimization methods suffer from two critical reliability bottlenecks: (1) reward…

Computation and Language · Computer Science 2026-05-14 Leyi Pan , Shuchang Tao , Yunpeng Zhai , Zheyu Fu , Liancheng Fang , Minghua He , Lingzhe Zhang , Zhaoyang Liu , Bolin Ding , Aiwei Liu , Lijie Wen

Search-augmented large language models (LLMs) trained with reinforcement learning (RL) have achieved strong results on open-domain question answering (QA), but training still remains a significant challenge. The optimization is often…

Computation and Language · Computer Science 2026-03-25 Yutao Xie , Nathaniel Thomas , Nicklas Hansen , Yang Fu , Li Erran Li , Xiaolong Wang

Credit assignment, the process of attributing credit or blame to individual agents for their contributions to a team's success or failure, remains a fundamental challenge in multi-agent reinforcement learning (MARL), particularly in…

Existing robotic foundation policies are trained primarily via large-scale imitation learning. While such models demonstrate strong capabilities, they often struggle with long-horizon tasks due to distribution shift and error accumulation.…

Tool use represents a critical capability for AI agents, with recent advances focusing on leveraging reinforcement learning (RL) to scale up the explicit reasoning process to achieve better performance. However, there are some key…

Artificial Intelligence · Computer Science 2026-03-17 Yirong Zeng , Xiao Ding , Yufei Liu , Yuxian Wang , Qunyao Du , Yutai Hou , Wu Ning , Haonan Song , Duyu Tang , Dandan Tu , Bing Qin , Ting Liu

Recent advancements in reasoning-focused language models such as OpenAI's O1 and DeepSeek-R1 have shown that scaling test-time computation-through chain-of-thought reasoning and iterative exploration-can yield substantial improvements on…

The Inverse Reinforcement Learning (\textit{IRL}) problem has seen rapid evolution in the past few years, with important applications in domains like robotics, cognition, and health. In this work, we explore the inefficacy of current IRL…

Machine Learning · Computer Science 2022-09-28 Raeid Saqur

A fundamental challenge in multi-agent reinforcement learning (MARL) is to learn the joint policy in an extremely large search space, which grows exponentially with the number of agents. Moreover, fully decentralized policy factorization…

Multiagent Systems · Computer Science 2024-01-24 Zhiyuan Li , Wenshuai Zhao , Lijun Wu , Joni Pajarinen

Reinforcement learning has emerged as an effective paradigm for training large language models to interleave reasoning with search engine calls. However, existing approaches face a fundamental credit assignment problem: methods like…

Computation and Language · Computer Science 2026-04-02 Chris Samarinas , Haw-Shiuan Chang , Hamed Zamani

Deep Reinforcement Learning (DRL) is a frequently employed technique to solve scheduling problems. Although DRL agents ace at delivering viable results in short computing times, their reasoning remains opaque. We conduct a case study where…

Artificial Intelligence · Computer Science 2024-09-02 Daniel Fischer , Hannah M. Hüsener , Felix Grumbach , Lukas Vollenkemper , Arthur Müller , Pascal Reusch

Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL) that reason and act in interactive environments. However, sparse and sometimes unverifiable rewards make it extremely…

Computation and Language · Computer Science 2025-09-30 Xiaoqian Liu , Ke Wang , Yuchuan Wu , Fei Huang , Yongbin Li , Junge Zhang , Jianbin Jiao

Inverse Reinforcement Learning (IRL) learns a reward function to explain expert demonstrations. Modern IRL methods often use the adversarial (minimax) formulation that alternates between reward and policy optimization, which often lead to…

Machine Learning · Computer Science 2025-10-14 Yang Chen , Menglin Zou , Jiaqi Zhang , Yitan Zhang , Junyi Yang , Gael Gendron , Libo Zhang , Jiamou Liu , Michael J. Witbrock

Reinforcement learning agents are fundamentally limited by the quality of the reward functions they learn from, yet reward design is often overlooked under the assumption that a well-defined reward is readily available. However, in…

Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning can lead to false positives for…

We consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and,…

Machine Learning · Computer Science 2022-10-19 Shangtong Zhang , Yi Wan , Richard S. Sutton , Shimon Whiteson

Open-domain table question answering traditionally relies on a two-stage pipeline: static table retrieval followed by a closed-domain answer. In contrast, we propose an end-to-end agentic framework that embeds multi-turn tool calls-using a…

Computation and Language · Computer Science 2025-07-08 Zipeng Qiu

Reinforcement learning (RL) has shown significant promise for sequential portfolio optimization tasks, such as stock trading, where the objective is to maximize cumulative returns while minimizing risks using historical data. However,…

Machine Learning · Computer Science 2025-05-20 Haochen Yuan , Minting Pan , Yunbo Wang , Siyu Gao , Philip S. Yu , Xiaokang Yang