Optimal Convergence in Multi-Agent MDPs.
Peter VrancxKatja VerbeeckAnn NowéPublished in: KES (3) (2007)
Keyphrases
- multi agent
- reinforcement learning
- dynamic programming
- markov decision processes
- average cost
- convergence rate
- finite horizon
- multi agent systems
- cooperative
- state space
- average reward
- optimal solution
- optimal control
- action sets
- heterogeneous agents
- planning under uncertainty
- partially observable markov decision processes
- single agent
- intelligent agents
- worst case
- least squares
- lower bound