Sample Efficient Policy Search for Optimal Stopping Domains. (arXiv:1702.06238v1 [cs.AI])

Arising naturally in many fields, optimal stopping problems consider the question of deciding when to stop an observation-generating process. 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.

from cs.AI updates on arXiv.org http://ift.tt/2kJEl2h
via IFTTT