Survey of Recent Multi-Agent Reinforcement Learning Algorithms Utilizing Centralized Training.
Piyush K. SharmaRolando FernandezErin G. ZaroukianMichael DorothyAnjon BasakDerrik E. AsherPublished in: CoRR (2021)
Keyphrases
- multi agent systems
- reinforcement learning algorithms
- multi agent
- reinforcement learning
- multi agent environments
- cooperative
- model free
- markov decision processes
- state space
- eligibility traces
- reinforcement learning methods
- reinforcement learning problems
- markov games
- temporal difference
- multiagent systems
- neural network
- function approximation
- policy search
- training set
- decision making
- stochastic games
- learning algorithm
- multiagent reinforcement learning
- machine learning
- single agent
- reward function
- dynamic environments
- supervised learning
- dynamic programming
- partially observable environments