Importance Sampling for Fair Policy Selection /

Importance Sampling for Fair Policy Selection / Shayan Doroudi, Philip S. Thomas and Emma Brunskill.

We consider the problem of off-policy policy selection in reinforcement learning: using historical data generated from running one policy to compare two or more policies. We show that approaches based on importance sampling can be "unfair"--they can select the worse of two policies more of...

Full description

Saved in:
Bibliographic Details
Online Access: Full Text (via ERIC)
Main Authors: Doroudi, Shayan, Thomas, Philip S. (Author), Brunskill, Emma (Author)
Format: eBook
Language:English
Published: [Place of publication not identified] : Distributed by ERIC Clearinghouse, 2017.
Subjects:
Sampling.
Policy Formation.
Policy Analysis.
Reinforcement.
Mathematics.
Computation.
Evaluation.

Internet

Full Text (via ERIC)

Online

Holdings details from Online
Call Number: ED586042
ED586042 Available

Similar Items