@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{UAI23,
author={Dustin Morrill and Thomas J.\ Walsh and Daniel Hernandez and Peter R.\ Wurman and Peter Stone},
title={Composing Efficient, Robust Tests for Policy Selection},
BookTitle={The 39th Conference on Uncertainty in Artificial Intelligence (UAI)},
location={Pittsburgh, PA, USA},
month={August},
year={2023},
abstract={
          Modern reinforcement learning systems produce many
          high-quality policies throughout the learning
          process. However, to choose which policy to actually deploy
          in the real world, they must be tested under an intractable
          number of environmental conditions. We introduce RPOSST, an
          algorithm to select a small set of test cases from a larger
          pool based on a relatively small number of sample
          evaluations. RPOSST treats the test case selection problem
          as a two-player game and optimizes a solution with provable
          $k$-of-$N$ robustness, bounding the error relative to a test
          that used all the test cases in the pool.  Empirical results
          demonstrate that RPOSST finds a small set of test cases that
          identify high quality policies in a toy one-shot game, poker
          datasets, and a high-fidelity racing simulator.
	  },
wwwnote={<a href="https://youtu.be/XkC9QR3Dil8">short video presentation</a>, <a href="https://www.auai.org/uai2023/posters/257.pdf">poster</a>},
}