Sample Efficient Policy Search for Optimal Stopping Domains

Sample Efficient Policy Search for Optimal Stopping Domains

Karan Goel, Christoph Dann, Emma Brunskill

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Main track. Pages 1711-1717. https://doi.org/10.24963/ijcai.2017/237

Optimal stopping problems consider the question of deciding when to stop an observation-generating process in order to maximize a return. We examine the problem of simultaneously learning and planning in such domains, when data is collected directly from the environment. We propose GFSE, a simple and flexible model-free policy search method that reuses data for sample efficiency by leveraging problem structure. We bound the sample complexity of our approach to guarantee uniform convergence of policy value estimates, tightening existing PAC bounds to achieve logarithmic dependence on horizon length for our setting. We also examine the benefit of our method against prevalent model-based and model-free approaches on 3 domains taken from diverse fields.
Keywords:
Machine Learning: Reinforcement Learning
Uncertainty in AI: Markov Decision Processes
Uncertainty in AI: Sequential Decision Making