Zap Q-Learning for Optimal Stopping.
Shuhang ChenAdithya M. DevrajAna BusicSean P. MeynPublished in: ACC (2020)
Keyphrases
- optimal stopping
- finite horizon
- optimal policy
- reinforcement learning
- brownian motion
- state space
- multi agent
- markov decision processes
- learning algorithm
- differential equations
- dynamic programming
- long run
- infinite horizon
- markov decision process
- markov chain
- diffusion process
- production system
- finite state
- heavy traffic
- image processing