Show simple item record

dc.contributor.authorRamakrishnan, Ramya
dc.contributor.authorKamar, Ece
dc.contributor.authorDey, Debadeepta
dc.contributor.authorShah, Julie A
dc.contributor.authorHorvitz, Eric
dc.date.accessioned2020-06-18T21:32:43Z
dc.date.available2020-06-18T21:32:43Z
dc.date.issued2018
dc.identifier.isbn978-1-4503-5649-7
dc.identifier.issn2523-5699
dc.identifier.urihttps://hdl.handle.net/1721.1/125874
dc.description.abstractAgents trained in simulation may make errors in the real world due to mismatches between training and execution environments. These mistakes can be dangerous and difficult to discover because the agent cannot predict them a priori. We propose using oracle feedback to learn a predictive model of these blind spots to reduce costly errors in real-world applications. We focus on blind spots in reinforcement learning (RL) that occur due to incomplete state representation: The agent does not have the appropriate features to represent the true state of the world and thus cannot distinguish among numerous states. We formalize the problem of discovering blind spots in RL as a noisy supervised learning problem with class imbalance. We learn models to predict blind spots in unseen regions of the state space by combining techniques for label aggregation, calibration, and supervised learning. The models take into consideration noise emerging from different forms of oracle feedback, including demonstrations and corrections. We evaluate our approach on two domains and show that it achieves higher predictive performance than baseline methods, and that the learned model can be used to selectively query an oracle at execution time to prevent errors. We also empirically analyze the biases of various feedback types and how they influence the discovery of blind spots.en_US
dc.language.isoen
dc.relation.isversionofhttps://dl.acm.org/doi/10.5555/3237383.3237849en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourcearXiven_US
dc.titleDiscovering blind spots in reinforcement learningen_US
dc.typeArticleen_US
dc.identifier.citationRamakrishnan, Ramya, et al., "Discovering blind spots in reinforcement learning." AAMAS '18: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, Stockholm, Sweden, July 2018 (New York, N.Y.: Association for Computing Machinery, 2018) url https://dl.acm.org/doi/10.5555/3237383.3237849 ©2018 Author(s)en_US
dc.relation.journalAAMAS '18: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systemsen_US
dc.eprint.versionOriginal manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dc.date.updated2019-10-31T18:44:48Z
dspace.date.submission2019-10-31T18:44:51Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record