A First Step Towards Behavioral Coaching for Managing Stress: A Case Study on Optimal Policy Estimation with Multi-stage Threshold Q-learning.
Xinyu HuPei-Yun Sabrina HsuehChing-Hua ChenKeith M. DiazYing-Kuen K. CheungMin QianPublished in: AMIA (2017)
Keyphrases
- multistage
- optimal policy
- reinforcement learning
- state space
- decision problems
- dynamic programming
- markov decision processes
- production system
- state dependent
- finite horizon
- stochastic optimization
- lot sizing
- infinite horizon
- long run
- single stage
- finite state
- markov decision process
- sufficient conditions
- long run average cost
- average cost
- control policies
- policy iteration
- asymptotically optimal
- average reward
- lost sales
- reward function
- production line
- steady state