FACMAC: Factored Multi-Agent Centralised Policy Gradients.
Bei PengTabish RashidChristian Schröder de WittPierre-Alexandre KamiennyPhilip H. S. TorrWendelin BoehmerShimon WhitesonPublished in: NeurIPS (2021)
Keyphrases
- multi agent
- cooperative
- multi agent systems
- optimal policy
- reinforcement learning
- state space
- intelligent agents
- data sets
- policy making
- asymptotically optimal
- multiagent systems
- multi agent coordination
- management policies
- decision processes
- markov decision process
- single agent
- image gradient
- expected cost
- information systems