Linear Programming and Zero-Sum Two-Person Undiscounted Semi-Markov Games.
Prasenjit MondalPublished in: Asia Pac. J. Oper. Res. (2015)
Keyphrases
- search space
- markov games
- linear programming
- markov decision processes
- markov decision problems
- state space
- stochastic games
- multiagent reinforcement learning
- dynamic programming
- optimal solution
- markov decision process
- policy iteration
- reinforcement learning algorithms
- linear program
- optimal policy
- infinite horizon
- average reward
- finite state
- mathematical programming
- average cost
- reinforcement learning
- objective function
- control problems
- machine learning
- np hard
- partially observable
- decision problems
- markov chain
- optimal stopping