Certainty equivalence for imperfect information finite state-space stochastic games.
William M. McEneaneyPublished in: CDC (2004)
Keyphrases
- stochastic games
- finite state
- imperfect information
- markov decision processes
- markov chain
- optimal policy
- game theoretic
- average reward
- model checking
- policy iteration
- average cost
- reinforcement learning algorithms
- state space
- nash equilibria
- reinforcement learning
- game tree
- multi agent
- infinite horizon
- partially observable
- markov decision process
- search space
- long run
- finite automata
- incomplete information
- dynamic programming