Optimal Policies for Quantum Markov Decision Processes.
Mingsheng YingYuan FengShenggang YingPublished in: Int. J. Autom. Comput. (2021)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- reinforcement learning
- infinite horizon
- dynamic programming
- decision problems
- state space
- finite horizon
- policy iteration
- average reward
- markov decision process
- average cost
- state dependent
- partially observable
- reinforcement learning algorithms
- long run
- multistage
- decision processes
- control policies
- initial state
- action space
- inventory level
- learning algorithm
- reward function
- discount factor
- lost sales
- sufficient conditions
- markov decision problems
- expected reward
- total reward
- discounted reward
- semi markov decision processes