Myopic Solutions of Markov Decision Processes and Stochastic Games.
Matthew J. SobelPublished in: Oper. Res. (1981)
Keyphrases
- markov decision processes
- stochastic games
- infinite horizon
- average reward
- dynamic programming
- optimal policy
- reinforcement learning
- state space
- reinforcement learning algorithms
- finite state
- multiagent reinforcement learning
- policy iteration
- average cost
- markov decision process
- finite horizon
- action space
- partially observable
- reward function
- machine learning
- optimal solution
- nash equilibria
- multi agent systems