Quantum Policy Iteration via Amplitude Estimation and Grover Search - Towards Quantum Advantage for Reinforcement Learning.
Simon WiedemannDaniel HeinSteffen UdluftChristian MendlPublished in: CoRR (2022)
Keyphrases
- policy iteration
- reinforcement learning
- markov decision processes
- model free
- temporal difference
- optimal policy
- fixed point
- search algorithm
- stochastic approximation
- markov decision process
- least squares
- approximate dynamic programming
- function approximation
- policy evaluation
- markov decision problems
- actor critic
- learning algorithm
- state space
- sample path
- finite state
- reinforcement learning algorithms
- search space
- average reward
- temporal difference learning
- neural network
- optimal control
- multi agent
- approximate policy iteration
- convergence rate
- stereo matching