Core Nonemptiness of Stratified Pooling Games: A Structured Markov Decision Process Approach.
Loe SchlicherMarco SlikkerWillem van JaarsveldGeert-Jan van HoutumPublished in: Math. Oper. Res. (2020)
Keyphrases
- markov decision process
- state space
- markov decision processes
- coalitional games
- optimal policy
- finite horizon
- infinite horizon
- policy iteration
- reinforcement learning
- transition matrices
- temporal difference learning
- game theory
- video games
- stochastic games
- multiagent systems
- reward function
- initial state
- decision making
- transition probabilities
- game theoretic
- dynamic programming
- machine learning
- game playing
- state variables
- nash equilibrium
- multistage
- information extraction