On discounted AR-AT semi-Markov games and its complementarity formulations.
Prasenjit MondalS. SinhaS. K. NeogyA. K. DasPublished in: Int. J. Game Theory (2016)
Keyphrases
- markov games
- markov decision processes
- markov decision process
- augmented reality
- optimal policy
- infinite horizon
- multiagent reinforcement learning
- policy iteration
- state space
- finite state
- dynamic programming
- reinforcement learning
- finite horizon
- average cost
- reinforcement learning algorithms
- stochastic games
- incomplete information
- average reward
- reward function
- partially observable
- long run
- cooperative
- decision problems
- generative model
- machine learning