English
Related papers

Related papers: Fixing Incomplete Value Function Decomposition for…

200 papers

Recent advances in recommender systems have shown that user-system interaction essentially formulates long-term optimization problems, and online reinforcement learning can be adopted to improve recommendation performance. The general…

Information Retrieval · Computer Science 2025-02-04 Xiaobei Wang , Shuchang Liu , Qingpeng Cai , Xiang Li , Lantao Hu , Han li , Guangming Xie

Representation learning and exploration are among the key challenges for any deep reinforcement learning agent. In this work, we provide a singular value decomposition based method that can be used to obtain representations that preserve…

Machine Learning · Computer Science 2023-05-03 Yash Chandak , Shantanu Thakoor , Zhaohan Daniel Guo , Yunhao Tang , Remi Munos , Will Dabney , Diana L Borsa

Value decomposition has long been a fundamental technique in multi-agent dynamic programming and reinforcement learning (RL). Specifically, the value function of a global state $(s_1,s_2,\ldots,s_N)$ is often approximated as the sum of…

Machine Learning · Computer Science 2025-11-14 Shuze Chen , Tianyi Peng

Current value-based multi-agent reinforcement learning methods optimize individual Q values to guide individuals' behaviours via centralized training with decentralized execution (CTDE). However, such expected, i.e., risk-neutral, Q value…

Machine Learning · Computer Science 2021-03-23 Wei Qiu , Xinrun Wang , Runsheng Yu , Xu He , Rundong Wang , Bo An , Svetlana Obraztsova , Zinovi Rabinovich

Coordination is one of the most difficult aspects of multi-agent reinforcement learning (MARL). One reason is that agents normally choose their actions independently of one another. In order to see coordination strategies emerging from the…

Machine Learning · Computer Science 2023-01-16 Matteo Gallici , Mario Martin , Ivan Masmitja

We investigate the problem of distributed training under partial observability, whereby cooperative multi-agent reinforcement learning agents (MARL) maximize the expected cumulative joint reward. We propose distributed value decomposition…

Machine Learning · Computer Science 2025-02-12 Guilherme S. Varela , Alberto Sardinha , Francisco S. Melo

This paper concerns imitation learning (IL) (i.e, the problem of learning to mimic expert behaviors from demonstrations) in cooperative multi-agent systems. The learning problem under consideration poses several challenges, characterized by…

Machine Learning · Computer Science 2023-10-11 The Viet Bui , Tien Mai , Thanh Hong Nguyen

Credit assignment remains a fundamental challenge in multi agent reinforcement learning (MARL) and is commonly addressed through value decomposition under the centralized training with decentralized ex ecution (CTDE) paradigm. However,…

Multiagent Systems · Computer Science 2026-03-17 Yuanjun Li , Zhouyang Jiang , Bin Zhang , Mingchao Zhang , Junhao Zhao , Zhiwei Xu

In fully cooperative multi-agent reinforcement learning (MARL) settings, the environments are highly stochastic due to the partial observability of each agent and the continuously changing policies of the other agents. To address the above…

Multiagent Systems · Computer Science 2021-12-23 Wei-Fang Sun , Cheng-Kuang Lee , Chun-Yi Lee

VDN and QMIX are two popular value-based algorithms for cooperative MARL that learn a centralized action value function as a monotonic mixing of per-agent utilities. While this enables easy decentralization of the learned policy, the…

Machine Learning · Computer Science 2021-06-11 Tarun Gupta , Anuj Mahajan , Bei Peng , Wendelin Böhmer , Shimon Whiteson

Deep reinforcement learning methods have shown great performance on many challenging cooperative multi-agent tasks. Two main promising research directions are multi-agent value function decomposition and multi-agent policy gradients. In…

Artificial Intelligence · Computer Science 2021-05-11 Yuan Pu , Shaochen Wang , Rui Yang , Xin Yao , Bin Li

Future generations of mobile networks are expected to contain more and more antennas with growing complexity and more parameters. Optimizing these parameters is necessary for ensuring the good performance of the network. The scale of mobile…

Networking and Internet Architecture · Computer Science 2023-02-03 Maxime Bouton , Jaeseong Jeong , Jose Outes , Adriano Mendo , Alexandros Nikou

Decomposition methods have been proposed to approximate solutions to large sequential decision making problems. In contexts where an agent interacts with multiple entities, utility decomposition can be used to separate the global objective…

Machine Learning · Computer Science 2019-04-24 Maxime Bouton , Kyle Julian , Alireza Nakhaei , Kikuo Fujimura , Mykel J. Kochenderfer

We present a general convergent class of reinforcement learning algorithms that is founded on two distinct principles: (1) mapping value estimates to a different space using arbitrary functions from a broad class, and (2) linearly…

Machine Learning · Computer Science 2022-03-18 Mehdi Fatemi , Arash Tavakoli

We explore value-based solutions for multi-agent reinforcement learning (MARL) tasks in the centralized training with decentralized execution (CTDE) regime popularized recently. However, VDN and QMIX are representative examples that use the…

Machine Learning · Computer Science 2019-05-15 Kyunghwan Son , Daewoo Kim , Wan Ju Kang , David Earl Hostallero , Yung Yi

We formulate an efficient approximation for multi-agent batch reinforcement learning, the approximated multi-agent fitted Q iteration (AMAFQI). We present a detailed derivation of our approach. We propose an iterative policy search and show…

Machine Learning · Computer Science 2023-04-06 Antoine Lesage-Landry , Duncan S. Callaway

Reinforcement learning (RL) is an effective framework for solving sequential decision-making tasks. However, applying RL methods in medical care settings is challenging in part due to heterogeneity in treatment response among patients. Some…

Machine Learning · Computer Science 2026-05-12 Aishwarya Mandyam , Andrew Jones , Jiayu Yao , Krzysztof Laudanski , Barbara Engelhardt

Value factorization is a popular paradigm for designing scalable multi-agent reinforcement learning algorithms. However, current factorization methods make choices without full justification that may limit their performance. For example,…

Artificial Intelligence · Computer Science 2024-09-11 Enrico Marchesini , Andrea Baisero , Rupali Bhati , Christopher Amato

Multi-agent systems are characterized by environmental uncertainty, varying policies of agents, and partial observability, which result in significant risks. In the context of Multi-Agent Reinforcement Learning (MARL), learning coordinated…

Multiagent Systems · Computer Science 2024-03-22 Siqi Shen , Chennan Ma , Chao Li , Weiquan Liu , Yongquan Fu , Songzhu Mei , Xinwang Liu , Cheng Wang

Many real-world applications involve some agents that fall into two teams, with payoffs that are equal within the same team but of opposite sign across the opponent team. The so-called two-team zero-sum Markov games (2t0sMGs) can be…

Artificial Intelligence · Computer Science 2024-02-02 Guangzheng Hu , Yuanheng Zhu , Haoran Li , Dongbin Zhao