Quantum reinforcement learning via policy iteration.
El Amine CherratIordanis KerenidisAnupam PrakashPublished in: Quantum Mach. Intell. (2023)
Keyphrases
- policy iteration
- reinforcement learning
- markov decision processes
- model free
- optimal policy
- temporal difference
- sample path
- markov decision process
- policy evaluation
- stochastic approximation
- reinforcement learning algorithms
- approximate dynamic programming
- state space
- fixed point
- average reward
- function approximation
- temporal difference learning
- least squares
- actor critic
- finite state
- infinite horizon
- discounted reward
- convergence rate
- partially observable
- markov decision problems
- approximate policy iteration
- multi agent
- stochastic games
- machine learning
- optimal control
- supervised learning
- control problems
- state and action spaces
- evaluation function