<  Back to the Polytechnique Montréal portal

The LoCA regret: A consistent metric to evaluate model-based behavior in reinforcement learning

Harm Van Seijen, Hadi Nekoei, Evan Racah and Sarath Chandar Anbil Parthipan

Paper (2020)

This item is not archived in PolyPublie
Department: Department of Computer Engineering and Software Engineering
PolyPublie URL: https://publications.polymtl.ca/48689/
Conference Title: 34th Conference on Neural Information Processing Systems (NeurIPS 2020)
Conference Date(s): 2020-12-06 - 2020-12-12
Publisher: Neural Information Processing Systems Foundation
Date Deposited: 18 Apr 2023 15:01
Last Modified: 25 Sep 2024 16:37
Cite in APA 7: Van Seijen, H., Nekoei, H., Racah, E., & Anbil Parthipan, S. C. (2020, December). The LoCA regret: A consistent metric to evaluate model-based behavior in reinforcement learning [Paper]. 34th Conference on Neural Information Processing Systems (NeurIPS 2020).

Statistics

Stats are not available on this system.

Repository Staff Only

View Item View Item