Warm-Start Variational Quantum Policy Iteration.
Nico MeyerJakob MurauerAlexander PopovChristian UfrechtAxel PlingeChristopher MutschlerDaniel D. SchererPublished in: CoRR (2024)
Keyphrases
- policy iteration
- markov decision processes
- model free
- reinforcement learning
- least squares
- optimal policy
- sample path
- fixed point
- finite state
- average reward
- markov decision process
- temporal difference
- policy evaluation
- infinite horizon
- optical flow
- image segmentation
- optimal control
- convergence rate
- linear programming
- discounted reward
- markov decision problems
- decision making
- computer vision