Quantum Reinforcement Learning via Policy Iteration.
El Amine CherratIordanis KerenidisAnupam PrakashPublished in: CoRR (2022)
Keyphrases
- policy iteration
- reinforcement learning
- markov decision processes
- model free
- optimal policy
- temporal difference
- policy evaluation
- sample path
- approximate dynamic programming
- reinforcement learning algorithms
- stochastic approximation
- fixed point
- markov decision process
- average reward
- function approximation
- least squares
- state space
- temporal difference learning
- actor critic
- markov decision problems
- multi agent
- control problems
- optimal control
- machine learning
- finite state
- learning algorithm
- action selection
- neural network
- approximate policy iteration
- reward function
- partially observable
- long run
- action space
- function approximators
- transfer learning
- multistage
- graph cuts
- linear programming
- supervised learning
- dynamic programming