Decentralized Multi-Agent Actor-Critic with Generative Inference.
Kevin CorderManuel M. VindiolaKeith DeckerPublished in: CoRR (2019)
Keyphrases
- multi agent
- actor critic
- reinforcement learning
- policy gradient
- single agent
- cooperative
- optimal control
- reinforcement learning algorithms
- temporal difference
- multi agent systems
- bayesian networks
- generative model
- state space
- neuro fuzzy
- approximate dynamic programming
- function approximation
- multiple agents
- partially observable markov decision processes
- gradient method
- control strategy
- dynamic programming