Quantum Markov Decision Processes Part I: General Theory, Approximations, and Classes of Policies.
Naci SaldiSina SanjariSerdar YükselPublished in: CoRR (2024)
Keyphrases
- markov decision processes
- general theory
- optimal policy
- markov decision process
- reward function
- average cost
- decision processes
- finite state
- reinforcement learning
- state space
- morphological operators
- discounted reward
- policy iteration
- total reward
- finite horizon
- policy evaluation
- dynamic programming
- decentralized control
- transition matrices
- expected reward
- infinite horizon
- stationary policies
- partially observable markov decision processes
- partially observable
- decision theoretic planning
- long run
- markov decision problems
- reinforcement learning algorithms
- planning under uncertainty
- average reward
- hierarchical reinforcement learning
- stable models
- state abstraction
- sufficient conditions
- first order logic
- data mining
- state and action spaces