Artificial Intelligence
多智能体强化学习
Multi-agent Reinforcement LearningA subfield of machine learning where multiple agents learn to interact within an environment to maximize cumulative rewards. / 机器学习的一个子领域，其中多个智能体在环境中交互以最大化累积奖励。
- Knowledge type
- 数学理论
- First proposed or discovered
- Proposer
- Turkey Farm member
- Creator
- 农场主
- Last updated
- 2026-10-23 07:00:32
Sub-knowledge points
Markov Decision Processes (MDP)Multi-agent Markov Decision Processes (MMDP)Cooperative vs. Competitive settings
Higher-order knowledge points
Main parameters and performance indicators
agents: number of interacting entitiesenvironment: state space and action spacerewards: scalar feedback signalscommunication constraints: limitations in data exchange
Open problems
scalability with increasing agent countcommunication efficiency under constraintstheoretical convergence guarantees
Related literature
ranked by community starsEdge-enhanced graph attention-based multi-agent reinforcement learning for multi-UUV cooperative area protection under communication and sensing constraintsOpen source
Related products and links
No item recorded yet
Creation and modification trail
1 recordsRecord title: Multi-agent Reinforcement Learning.
Node update feedback
review required