.png){kind=icon}
返回
A Gradient-Based Reinforcement Learning Algorithm for Multiple Cooperative Agents
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2018.2878853.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multi-agent reinforcement learning (MARL) can be used to design intelligent agents for solving cooperative tasks. Within the MARL category, this paper proposes the probability of maximal reward based on the infinitesimal gradient ascent (PMR-IGA) algorithm to reach the maximal total reward in repeated games. Theoretical analyses show that in a finite-player-finite-action repeated game with two pure optimal joint actions where no common component action exists, both the optimal joint actions are stable critical points of the PMR-IGA model. Furthermore, we apply the Q-value function to estimate the gradient and derive the probability of maximal reward based on estimated gradient ascent (PMR-EGA) algorithm. Theoretical analyses and simulations of case studies of repeated games show that the maximal total reward can be achieved under any initial conditions. The PMR-EGA can be naturally extended to optimize cooperative stochastic games. Two stochastic games, i.e., box pushing and a distributed sensor network, are used as test beds. The simulations show that the PMR-EGA displays consistently an excellent performance for both stochastic games.
Keyword:
Multi-agent reinforcement learning
gradient ascent
Q-learning
cooperative tasks
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Adaptive Neural Network Control of AUVs With Control Input Nonlinearities Using Reinforcement Learning基于强化学习的auv控制输入非线性自适应神经网络控制OAAI
OAAI分享收藏A Deep Hierarchical Reinforcement Learning Algorithm in Partially Observable Markov Decision Processes.png)
IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏分享收藏A Distributed Actor-Critic Algorithm and Applications to Mobile Sensor Network Coordination Problems
PREAI
分享收藏
查看更多内容