Defining admissible rewards for high-confidence policy evaluation in batch reinforcement learning - researchr publication

researchr

You are not signed in
Sign in
Sign up

Niranjani Prasad, Barbara E. Engelhardt, Finale Doshi-Velez. Defining admissible rewards for high-confidence policy evaluation in batch reinforcement learning. In Marzyeh Ghassemi, editor, ACM CHIL '20: ACM Conference on Health, Inference, and Learning, Toronto, Ontario, Canada, April 2-4, 2020 [delayed]. pages 1-9, ACM, 2020. [doi]

Abstract is missing.

runs on WebDSL