Upper and Lower Bounds of Optimal Stopping for a Random Sequence: The Case of Finite Horizon.
Vladimir M. KhametovElena A. ShelemekhPublished in: Autom. Remote. Control. (2019)
Keyphrases
- optimal stopping
- finite horizon
- upper and lower bounds
- optimal policy
- infinite horizon
- upper bound
- markov decision processes
- brownian motion
- lower bound
- multistage
- lower and upper bounds
- markov decision process
- average cost
- sample complexity
- reinforcement learning
- finite state
- semi supervised
- asymptotically optimal
- state space
- dynamic programming