Pareto Actor-Critic for Equilibrium Selection in Multi-Agent Reinforcement Learning.
Filippos ChristianosGeorgios PapoudakisStefano V. AlbrechtPublished in: CoRR (2022)
Keyphrases
- multi agent reinforcement learning
- actor critic
- reinforcement learning
- multi agent
- learning agents
- policy gradient
- optimal control
- multi agent learning
- function approximation
- reinforcement learning algorithms
- stochastic games
- gradient method
- neuro fuzzy
- genetic algorithm
- multi agent systems
- cooperative
- neural network
- average reward
- optimal policy