Black-Box Policy Search with Probabilistic Programs. (arXiv:1507.04635v3 [stat.ML] UPDATED)

In this work, we explore how probabilistic programs can be used to represent policies in sequential decision problems. In this formulation, a probabilistic program is a black-box stochastic simulator for both the problem domain and the agent. We relate classic policy gradient techniques to recently introduced black-box variational methods which generalize to probabilistic program inference. We present case studies in the Canadian traveler problem, Rock Sample, and a benchmark for optimal diagnosis inspired by Guess Who. Each study illustrates how programs can efficiently represent policies using moderate numbers of parameters.

Donate to arXiv

from cs.AI updates on arXiv.org http://ift.tt/1gErlEI
via IFTTT