Metadata only
Date
2023Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, collected by other agents, we seek to obtain a (tight) lower bound on a policy’s performance. This is crucial when deciding whether a given policy satisfies certain minimal performance/safety criteria before it can be deployed in the real world. To this end, we introduce HAMBO, which builds on an uncertainty-aware learned model of the transition dynamics. To form a conservative estimate of the policy’s performance, HAMBO hallucinates worst-case trajectories that the policy may take, within the margin of the models’ epistemic confidence regions. We prove that the resulting COPE estimates are valid lower bounds, and, under regularity conditions, show their convergence to the true expected return. Finally, we discuss scalable variants of our approach based on Bayesian Neural Networks and empirically demonstrate that they yield reliable and tight lower bounds in various continuous control environments. Show more
Publication status
publishedExternal links
Book title
Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial IntelligenceJournal / series
Proceedings of Machine Learning ResearchVolume
Pages / Article No.
Publisher
PMLREvent
Organisational unit
03908 - Krause, Andreas / Krause, Andreas
Funding
815943 - Reliable Data-Driven Decision Making in Cyber-Physical Systems (EC)
180545 - NCCR Automation (phase I) (SNF)
More
Show all metadata
ETH Bibliography
yes
Altmetrics