Cooperative Markov decision processes: time consistency, greedy players satisfaction, and cooperation maintenance.
Konstantin AvrachenkovLaura CottatellucciLorenzo MaggiPublished in: Int. J. Game Theory (2013)
Keyphrases
- markov decision processes
- cooperative
- game theory
- dynamic programming
- optimal policy
- reinforcement learning
- finite state
- policy iteration
- search algorithm
- state space
- multi agent
- multi agent systems
- reachability analysis
- decision theoretic planning
- planning under uncertainty
- finite horizon
- action space
- transition matrices
- markov decision process
- reinforcement learning algorithms
- decision processes
- factored mdps
- average cost
- partially observable
- risk sensitive
- reward function
- average reward
- infinite horizon
- hill climbing
- function approximation
- machine learning