Adaptive Adversarial Multi-Armed Bandit Approach to Two-Person Zero-Sum Markov Games.
Hyeong Soo ChangJiaqiao HuMichael C. FuSteven I. MarcusPublished in: IEEE Trans. Autom. Control. (2010)
Keyphrases
- markov games
- markov decision processes
- multiagent reinforcement learning
- multi armed bandit
- reinforcement learning
- reinforcement learning algorithms
- markov decision process
- multi agent
- stochastic games
- control problems
- state space
- multiagent systems
- cooperative
- incomplete information
- multi armed bandits
- nash equilibrium
- game theory
- optimal policy
- adaptive control