Attention:The NSF Public Access Repository (PAR) system and access will be unavailable from 5:00 PM ET until 8:00 PM ET on Friday, September 11 due to maintenance. We apologize for the inconvenience.


Title: Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning
Award ID(s):
2106778
PAR ID:
10592994
Author(s) / Creator(s):
; ; ; ; ; ; ;
Publisher / Repository:
The Thirteenth International Conference on Learning Representations
Date Published:
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
  2. This article reviews distributionally robust optimization as a principled approach for constructing statistical estimators that hedge against deviations between training and deployment environments. It explains precise DRO interpretations of familiar methods such as AdaBoost, LASSO, ridge regression, and dropout, and clarifies the fundamental distinction between DRO and classical contamination-robust statistics. 
    more » « less