Composing Efficient, Robust Tests for Policy Selection

Dustin Morrill

Thomas Walsh

Daniel Hernandez

Peter R. Wurman

Peter Stone

UAI 2023



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.

Related Publications

Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning

AAAI, 2024
Zizhao Wang*, Caroline Wang*, Xuesu Xiao*, Yuke Zhu*, Peter Stone

Two desiderata of reinforcement learning (RL) algorithms are the ability to learn from relatively little experience and the ability to learn policies that generalize to a range of problem specifications. In factored state spaces, one approach towards achieving both goals is …

Minimum Coverage Sets for Training Robust Ad Hoc Teamwork Agents

AAAI, 2024
Arrasy Rahman*, Jiaxun Cui*, Peter Stone

Robustly cooperating with unseen agents and human partners presents significant challenges due to the diverse cooperative conventions these partners may adopt. Existing Ad Hoc Teamwork (AHT) methods address this challenge by training an agent with a population of diverse tea…

Learning Optimal Advantage from Preferences and Mistaking it for Reward

AAAI, 2024
W. Bradley Knox*, Stephane Hatgis-Kessell*, Sigurdur Orn Adalgeirsson*, Serena Booth*, Anca Dragan*, Peter Stone, Scott Niekum*

We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments---as used in reinforcement learning from human feedback (RLHF)---including those used to fine tune ChatGPT and other contemporary language models. Most recent work o…


Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.