Zero-Sum Markov Games with Random State-Actions-Dependent Discount Factors: Existence of Optimal Strategies.
David González-SánchezFernando Luque-VásquezJ. Adolfo Minjárez-SosaPublished in: Dyn. Games Appl. (2019)
Keyphrases
- optimal strategy
- markov games
- multiagent reinforcement learning
- markov decision processes
- multiagent systems
- decision problems
- stochastic games
- cooperative
- partially observable
- initial state
- state space
- reinforcement learning algorithms
- monte carlo
- multi agent
- mathematical models
- control problems
- state transitions
- adaptive control
- expected cost
- optimal solution
- search algorithm