← Search

Daniel Hernandez

2 accepted papers

2023

Composing Efficient, Robust Tests for Policy Selection

UAI 2023poster

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 s…

Cited by 0SourcePDFScholar