Efficient computation of discounted asymmetric information zero-sum stochastic games.
Lichun LiJeff S. ShammaPublished in: CDC (2015)
Keyphrases
- stochastic games
- efficient computation
- markov decision processes
- average reward
- infinite horizon
- optimal policy
- long run
- games with incomplete information
- reinforcement learning
- multiagent reinforcement learning
- finite horizon
- dynamic programming
- reinforcement learning algorithms
- computational efficiency
- nash equilibria
- finite state
- policy iteration
- state space
- partially observable
- repeated games
- markov chain
- sufficient conditions
- average cost
- model free
- learning automata
- query processing
- multi agent
- learning algorithm
- game theory
- decision problems