Centralized Training with Decentralized Execution Reinforcement Learning for Cooperative Multi-agent Systems with Communication Delay.
Takuma IkedaTakeshi ShibuyaPublished in: SICE (2022)
Keyphrases
- cooperative multi agent systems
- reinforcement learning
- multi agent reinforcement learning
- multi agent
- multi agent systems
- function approximation
- state space
- supervised learning
- peer to peer
- reinforcement learning algorithms
- dynamic programming
- learning algorithm
- multi agent learning
- training examples
- machine learning
- multiagent systems
- temporal difference
- real robot
- fully distributed
- cooperative
- markov decision processes
- learning problems
- data mining
- learning process
- learning agents
- peer to peer systems
- artificial intelligence