Interaction-driven Markov games for decentralized multiagent planning under uncertainty.
Matthijs T. J. SpaanFrancisco S. MeloPublished in: AAMAS (1) (2008)
Keyphrases
- planning under uncertainty
- markov games
- markov decision processes
- multi agent
- multiagent reinforcement learning
- dec pomdps
- reinforcement learning algorithms
- multiagent systems
- finite state
- decision theoretic
- dynamic programming
- ai planning
- reinforcement learning
- cooperative
- optimal policy
- state space
- partially observable markov decision processes
- dynamical systems
- markov decision process
- infinite horizon
- partially observable
- machine learning
- multi agent systems
- heuristic search
- special case