November 08, 2022
Adaptive curricula in reinforcement learning (RL) have proven effective for producing policies robust to discrepancies between the train and test environment. Recently, the Unsupervised Environment Design (UED) framework generalized RL curricula to generating sequences of entire environments, leading to new methods with robust minimax regret properties. Problematically, in partially-observable or stochastic settings, optimal policies may depend on the ground-truth distribution over aleatoric parameters of the environment in the intended deployment setting, while curriculum learning necessarily shifts the training distribution. We formalize this phenomenon as curriculum-induced covariate shift (CICS), and describe how its occurrence in aleatoric parameters can lead to suboptimal policies. Directly sampling these parameters from the ground-truth distribution avoids the issue, but thwarts curriculum learning. We propose SAMPLR, a minimax regret UED method that optimizes the ground-truth utility function, even when the underlying training data is biased due to CICS. We prove, and validate on challenging domains, that our approach preserves optimality under the ground-truth distribution, while promoting robustness across the full range of environment settings.
Written by
Minqi Jiang
Andrei Lupu
Heinrich Küttler
Jack Parker-Holder
Jakob Foerster
Michael Dennis
Tim Rocktäschel
egrefen@gmail.com
Publisher
NeurIPS
Research Topics
June 27, 2025
Vasu Agrawal, Akinniyi Akinyemi, Kathryn Alvero, Morteza Behrooz, Julia Buffalini, Fabio Maria Carlucci, Joy Chen, Junming Chen, Zhang Chen, Shiyang Cheng, Praveen Chowdary, Joe Chuang, Antony D'Avirro, Jon Daly, Ning Dong, Mark Duppenthaler, Cynthia Gao, Jeff Girard, Martin Gleize, Sahir Gomez, Hongyu Gong, Srivathsan Govindarajan, Brandon Han, Sen He, Denise Hernandez, Yordan Hristov, Rongjie Huang, Hirofumi Inaguma, Somya Jain, Raj Janardhan, Qingyao Jia, Christopher Klaiber, Dejan Kovachev, Moneish Kumar, Hang Li, Yilei Li, Pavel Litvin, Wei Liu, Guangyao Ma, Jing Ma, Martin Ma, Xutai Ma, Lucas Mantovani, Sagar Miglani, Sreyas Mohan, Louis-Philippe Morency, Evonne Ng, Kam-Woh Ng, Tu Anh Nguyen, Amia Oberai, Benjamin Peloquin, Juan Pino, Jovan Popovic, Omid Poursaeed, Fabian Prada, Alice Rakotoarison, Alexander Richard, Christophe Ropers, Safiyyah Saleem, Vasu Sharma, Alex Shcherbyna, Jie Shen, Anastasis Stathopoulos, Anna Sun, Paden Tomasello, Tuan Tran, Arina Turkatenko, Bo Wan, Chao Wang, Jeff Wang, Mary Williamson, Carleigh Wood, Tao Xiang, Yilin Yang, Zhiyuan Yao, Chen Zhang, Jiemin Zhang, Xinyue Zhang, Jason Zheng, Pavlo Zhyzheria, Jan Zikes, Michael Zollhoefer
June 27, 2025
June 13, 2025
Ido Guy, Daniel Haimovich, Fridolin Linder, Nastaran Okati, Lorenzo Perini, Niek Tax, Mark Tygert
June 13, 2025
June 11, 2025
Florian Bordes, Quentin Garrido, Justine Kao, Adina Williams, Mike Rabbat, Emmanuel Dupoux
June 11, 2025
June 11, 2025
Benno Krojer, Mojtaba Komeili, Candace Ross, Quentin Garrido, Koustuv Sinha, Nicolas Ballas, Mido Assran
June 11, 2025
Our approach
Latest news
Foundational models