中文
相关论文

相关论文: Value-based CTDE Methods in Symmetric Two-team Mar…

200 篇论文

Centralised training with decentralised execution is an important setting for cooperative deep multi-agent reinforcement learning due to communication constraints during execution and computational tractability in training. In this paper,…

机器学习 · 计算机科学 2020-01-22 Anuj Mahajan , Tabish Rashid , Mikayel Samvelyan , Shimon Whiteson

Existing value-factorized based Multi-Agent deep Reinforce-ment Learning (MARL) approaches are well-performing invarious multi-agent cooperative environment under thecen-tralized training and decentralized execution(CTDE) scheme,where all…

人工智能 · 计算机科学 2019-11-19 Runsheng Yu , Zhenyu Shi , Xinrun Wang , Rundong Wang , Buhong Liu , Xinwen Hou , Hanjiang Lai , Bo An

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…

机器学习 · 计算机科学 2021-03-23 Wei Qiu , Xinrun Wang , Runsheng Yu , Xu He , Rundong Wang , Bo An , Svetlana Obraztsova , Zinovi Rabinovich

We explore value decomposition solutions for multi-agent deep reinforcement learning in the popular paradigm of centralized training with decentralized execution(CTDE). As the recognized best solution to CTDE, Weighted QMIX is cutting-edge…

多智能体系统 · 计算机科学 2022-08-09 Kai Liu , Tianxian Zhang , Lingjiang Kong

Multi-agent reinforcement learning (MARL) has exploded in popularity in recent years. While numerous approaches have been developed, they can be broadly categorized into three main types: centralized training and execution (CTE),…

机器学习 · 计算机科学 2025-05-22 Christopher Amato

In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting,…

Training agents in multi-agent competitive games presents significant challenges due to their intricate nature. These challenges are exacerbated by dynamics influenced not only by the environment but also by opponents' strategies. Existing…

机器学习 · 计算机科学 2023-08-22 The Viet Bui , Tien Mai , Thanh Hong Nguyen

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…

多智能体系统 · 计算机科学 2025-01-22 Mengxian Li , Qi Wang , Yongjun Xu

Many advances in cooperative multi-agent reinforcement learning (MARL) are based on two common design principles: value decomposition and parameter sharing. A typical MARL algorithm of this fashion decomposes a centralized Q-function into…

人工智能 · 计算机科学 2022-08-09 Wei Fu , Chao Yu , Zelai Xu , Jiaqi Yang , Yi Wu

Centralized training with decentralized execution (CTDE) is a widely-used learning paradigm that has achieved significant success in complex tasks. However, partial observability issues and the absence of effectively shared signals between…

多智能体系统 · 计算机科学 2023-05-01 Dapeng Li , Zhiwei Xu , Bin Zhang , Guoliang Fan

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…

多智能体系统 · 计算机科学 2020-08-11 Xinghu Yao , Chao Wen , Yuhui Wang , Xiaoyang Tan

The partial alignment and conflict of autonomous agents lead to mixed-motive scenarios in many real-world applications. However, agents may fail to cooperate in practice even when cooperation yields a better outcome. One well known reason…

人工智能 · 计算机科学 2025-03-20 Shuhui Zhu , Baoxiang Wang , Sriram Ganapathi Subramanian , Pascal Poupart

Multi-agent reinforcement learning (MARL) has exploded in popularity in recent years. Many approaches have been developed but they can be divided into three main types: centralized training and execution (CTE), centralized training for…

机器学习 · 计算机科学 2024-12-22 Christopher Amato

The Centralized Training with Decentralized Execution (CTDE) paradigm has gained significant attention in multi-agent reinforcement learning (MARL) and is the foundation of many recent algorithms. However, decentralized policies operate…

多智能体系统 · 计算机科学 2025-08-19 Zhuofan Xu , Benedikt Bollig , Matthias Függer , Thomas Nowak , Vincent Le Dréau

In multi-agent reinforcement learning, the cooperative learning behavior of agents is very important. In the field of heterogeneous multi-agent reinforcement learning, cooperative behavior among different types of agents in a group is…

人工智能 · 计算机科学 2021-04-14 Taeyoung Kim , Luiz Felipe Vecchietti , Kyujin Choi , Sanem Sariel , Dongsoo Har

In multi-agent cooperative tasks, the presence of heterogeneous agents is familiar. Compared to cooperation among homogeneous agents, collaboration requires considering the best-suited sub-tasks for each agent. However, the operation of…

多智能体系统 · 计算机科学 2024-08-15 Songchen Fu , Shaojing Zhao , Ta Li , YongHong Yan

Team competition in multi-agent Markov games is an increasingly important setting for multi-agent reinforcement learning, due to its general applicability in modeling many real-life situations. Multi-agent actor-critic methods are the most…

多智能体系统 · 计算机科学 2023-01-18 Paramita Koley , Aurghya Maiti , Niloy Ganguly , Sourangshu Bhattacharya

Recent Multi-Agent Reinforcement Learning (MARL) literature has been largely focused on Centralized Training with Decentralized Execution (CTDE) paradigm. CTDE has been a dominant approach for both cooperative and mixed environments due to…

机器学习 · 计算机科学 2022-05-31 Vladimir Egorov , Aleksei Shpilman

Multi-agent reinforcement learning is an area of rapid advancement in artificial intelligence and machine learning. One of the important questions to be answered is how to conduct credit assignment in a multi-agent system. There have been…

多智能体系统 · 计算机科学 2024-02-26 Jianhong Wang

In many real-world settings, a team of agents must coordinate its behaviour while acting in a decentralised fashion. At the same time, it is often possible to train the agents in a centralised fashion where global state information is…

‹ 上一页 1 2 3 10 下一页 ›