K-spin Hamiltonian for quantum-resolvable Markov decision processes.
Eric B. JonesPeter A. GrafEliot KapitWesley B. JonesPublished in: Quantum Mach. Intell. (2020)
Keyphrases
- markov decision processes
- optimal policy
- dynamic programming
- transition matrices
- reinforcement learning
- policy iteration
- finite state
- finite horizon
- average cost
- reachability analysis
- partially observable
- state space
- planning under uncertainty
- decision processes
- markov decision process
- reinforcement learning algorithms
- risk sensitive
- decision theoretic planning
- factored mdps
- infinite horizon
- reward function
- model based reinforcement learning
- total reward
- action space
- state abstraction
- monte carlo