Capacity-Limited Decentralized Actor-Critic for Multi-Agent Games.
Tyler MalloyChris R. SimsTim KlingerMiao LiuMatthew RiemerGerald TesauroPublished in: CoG (2021)
Keyphrases
- multi agent
- actor critic
- reinforcement learning
- cooperative
- policy gradient
- single agent
- multi agent systems
- stochastic games
- optimal control
- game theory
- video games
- function approximation
- multiple agents
- temporal difference
- gradient method
- approximate dynamic programming
- neuro fuzzy
- nash equilibria
- policy iteration
- particle filter