English
Related papers

Related papers: TVDO: Tchebycheff Value-Decomposition Optimization…

200 papers

This paper focuses on finite-time (FT) convergent distributed algorithms for solving time-varying (TV) distributed optimization (TVDO). The objective is to minimize the sum of local TV cost functions subject to the possible TV constraints…

Optimization and Control · Mathematics 2023-09-04 Xinli Shi , Guanghui Wen , Xinghuo Yu

Value decomposition is a central approach in multi-agent reinforcement learning (MARL), enabling centralized training with decentralized execution by factorizing the global value function into local values. To ensure individual-global-max…

Machine Learning · Computer Science 2026-03-23 Tianmeng Hu , Yongzheng Cui , Rui Tang , Biao Luo , Ke Li

Value function decomposition is becoming a popular rule of thumb for scaling up multi-agent reinforcement learning (MARL) in cooperative games. For such a decomposition rule to hold, the assumption of the individual-global max (IGM)…

Machine Learning · Computer Science 2022-02-17 Zehao Dou , Jakub Grudzien Kuba , Yaodong Yang

Existing asynchronous MARL methods based on MacDec-POMDP typically construct training trajectory buffers by simply sampling limited and biased data at the endpoints of macro-actions, and directly apply conventional MARL methods on the…

Multiagent Systems · Computer Science 2025-07-15 Wenjing Zhang , Wei Zhang

Value function factorization has achieved great success in multi-agent reinforcement learning by optimizing joint action-value functions through the maximization of factorized per-agent utilities. To ensure Individual-Global-Maximum…

Multiagent Systems · Computer Science 2023-12-27 Huiqun Li , Hanhan Zhou , Yifei Zou , Dongxiao Yu , Tian Lan

Aggregation functions largely determine the convergence and diversity performance of multi-objective evolutionary algorithms in decomposition methods. Nevertheless, the traditional Tchebycheff function does not consider the matching…

Optimization and Control · Mathematics 2022-02-08 Xiaojun Zhou , Yuan Gao , Shengxiang Yang , Chunhua Yang , Jiajia Zhou

This paper investigates multi-objective reinforcement learning (MORL), which focuses on learning Pareto optimal policies in the presence of multiple reward functions. Despite MORL's significant empirical success, there is still a lack of…

Machine Learning · Computer Science 2024-07-25 Shuang Qiu , Dake Zhang , Rui Yang , Boxiang Lyu , Tong Zhang

Value factorisation is a useful technique for multi-agent reinforcement learning (MARL) in global reward game, however its underlying mechanism is not yet fully understood. This paper studies a theoretical framework for value factorisation…

Machine Learning · Computer Science 2023-01-10 Jianhong Wang , Yuan Zhang , Yunjie Gu , Tae-Kyun Kim

The rapid advancement of multi-agent reinforcement learning (MARL) has given rise to diverse training paradigms to learn the policies of each agent in the multi-agent system. The paradigms of decentralized training and execution (DTDE) and…

Multiagent Systems · Computer Science 2025-01-22 Mengxian Li , Qi Wang , Yongjun Xu

We explore value-based multi-agent reinforcement learning (MARL) in the popular paradigm of centralized training with decentralized execution (CTDE). CTDE has an important concept, Individual-Global-Max (IGM) principle, which requires the…

Machine Learning · Computer Science 2021-10-05 Jianhao Wang , Zhizhou Ren , Terry Liu , Yang Yu , Chongjie Zhang

Value decomposition (VD) methods have achieved remarkable success in cooperative multi-agent reinforcement learning (MARL). However, their reliance on the max operator for temporal-difference (TD) target calculation leads to systematic…

Multiagent Systems · Computer Science 2026-02-27 Yuanjun Li , Bin Zhang , Hao Chen , Zhouyang Jiang , Dapeng Li , Zhiwei Xu

We study the policy evaluation problem in multi-agent reinforcement learning, modeled by a Markov decision process. In this problem, the agents operate in a common environment under a fixed control policy, working together to discover the…

Optimization and Control · Mathematics 2020-01-13 Thinh T. Doan , Siva Theja Maguluri , Justin Romberg

Discrete-action reinforcement learning algorithms often falter in tasks with high-dimensional discrete action spaces due to the vast number of possible actions. A recent advancement leverages value-decomposition, a concept from multi-agent…

Machine Learning · Computer Science 2024-03-11 David Ireland , Giovanni Montana

Multi-objective learning (MOL) aims to learn under multiple potentially conflicting objectives and strike a proper balance. While recent preference-guided MOL methods often rely on additional optimization objectives or constraints, we…

Machine Learning · Computer Science 2026-03-27 Meitong Liu , Xiaoyuan Zhang , Chulin Xie , Kate Donahue , Han Zhao

The complexity of Pareto fronts imposes a great challenge on the convergence analysis of multi-objective optimization methods. While most theoretical convergence studies have addressed finite-set and/or discrete problems, others have…

Optimization and Control · Mathematics 2018-05-16 Abdullah Al-Dujaili , S. Suresh

Multi-agent reinforcement learning (MARL) provides a promising paradigm for coordinating multi-agent systems (MAS). However, most existing methods rely on restrictive assumptions, such as a fixed number of agents and fully synchronous…

Multiagent Systems · Computer Science 2026-02-17 Yexin Li , Jinjin Guo , Haoyu Zhang , Yuhan Zhao , Yiwen Sun , Zihao Jiao

Actor-critic methods for decentralized multi-agent reinforcement learning (MARL) facilitate collaborative optimal decision making without centralized coordination, thus enabling a wide range of applications in practice. To date, however,…

Machine Learning · Computer Science 2025-08-14 Zhiyao Zhang , Myeung Suk Oh , FNU Hairi , Ziyue Luo , Alvaro Velasquez , Jia Liu

Centralized Training with Decentralized Execution (CTDE) has been a popular paradigm in cooperative Multi-Agent Reinforcement Learning (MARL) settings and is widely used in many real applications. One of the major challenges in the training…

Artificial Intelligence · Computer Science 2022-01-25 Jiahui Li , Kun Kuang , Baoxiang Wang , Furui Liu , Long Chen , Fei Wu , Jun Xiao

Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution, where value-factorization methods enforce the individual-global-maximum (IGM) principle so that decentralized greedy…

Artificial Intelligence · Computer Science 2026-02-13 Chengrui Qu , Christopher Yeh , Kishan Panaganti , Eric Mazumdar , Adam Wierman

Learning a stable and generalizable centralized value function (CVF) is a crucial but challenging task in multi-agent reinforcement learning (MARL), as it has to deal with the issue that the joint action space increases exponentially with…

Multiagent Systems · Computer Science 2020-08-11 Xinghu Yao , Chao Wen , Yuhui Wang , Xiaoyang Tan
‹ Prev 1 2 3 10 Next ›