Structural relational inference actor-critic for multi-agent reinforcement learning.
Xianjie ZhangYu LiuXiujuan XuQiong HuangHangyu MaoAnil CariePublished in: Neurocomputing (2021)
Keyphrases
- multi agent reinforcement learning
- actor critic
- reinforcement learning
- stochastic games
- policy gradient
- learning agents
- average reward
- function approximation
- temporal difference
- reinforcement learning algorithms
- multi agent
- optimal control
- multi agent systems
- markov decision processes
- gradient method
- bayesian networks
- optimal policy
- state space
- multi agent learning
- dynamic bayesian networks
- learning automata
- cooperative
- dynamical systems