Multi-agent reinforcement learning as a rehearsal for decentralized planning.
Landon KraemerBikramjit BanerjeePublished in: Neurocomputing (2016)
Keyphrases
- multi agent reinforcement learning
- multi agent
- cooperative multi agent systems
- cooperative
- multi agent systems
- learning agents
- single agent
- domain independent
- planning problems
- stochastic games
- multi agent learning
- reinforcement learning
- heuristic search
- multiple agents
- distributed control
- search space
- fuzzy logic
- supervised learning
- optimal policy