Discovering blind spots in reinforcement learning
Name
1805.08966.pdf
Description
Submitted version
Size
1.45 MB
Format
Adobe PDF
Checksum (MD5)
ee48598e93f1f19e17e68a7764a4fa6e
Author(s)
Ramakrishnan, Ramya
Kamar, Ece
Dey, Debadeepta
Shah, Julie A
Horvitz, Eric
Date Issued
2018
Journal
AAMAS '18: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems
Citation
Ramakrishnan, 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)
Version
Original manuscript
Abstract
Agents 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.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Department of Aeronautics and Astronautics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://dl.acm.org/doi/10.5555/3237383.3237849
