Shared Experience Actor-Critic for Multi-Agent Reinforcement Learning.
Filippos ChristianosLukas SchäferStefano V. AlbrechtPublished in: CoRR (2020)
Keyphrases
- multi agent reinforcement learning
- actor critic
- reinforcement learning
- multi agent
- stochastic games
- policy gradient
- reinforcement learning algorithms
- learning agents
- temporal difference
- neuro fuzzy
- average reward
- cooperative
- state space
- gradient method
- model free
- optimal control
- function approximation
- artificial intelligence
- long run
- neural network
- policy iteration
- markov decision processes
- multi agent systems
- multi agent learning
- optimal policy
- dynamic programming
- learning algorithm