Heuristic algorithm for nested Markov decision process: Solution quality and computational complexity.
Sefakor FianuLauren B. DavisPublished in: Comput. Oper. Res. (2023)
Keyphrases
- markov decision process
- state space
- markov decision processes
- infinite horizon
- optimal policy
- decision problems
- reinforcement learning
- finite horizon
- temporal difference learning
- transition matrices
- multiagent systems
- initial state
- learning algorithm
- model checking
- em algorithm
- optimal control
- computational complexity