Stabilizing Unsupervised Environment Design with a Learned Adversary

v1v2 (latest)

Stabilizing Unsupervised Environment Design with a Learned Adversary

21 August 2023

Ishita Mediratta

Jack Parker-Holder

Eugene Vinitsky

Tim Rocktaschel

ArXiv (abs)PDF HTML

Papers citing "Stabilizing Unsupervised Environment Design with a Learned Adversary"

13 / 13 papers shown

Title
TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design Geonwoo Cho Jaegyun Im Jihwan Lee Hojun Yi Sejin Kim Sundong Kim 186 0 0 24 Jun 2025
Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination Kunal Jha Wilka Carvalho Yancheng Liang S. Du Max Kleiman-Weiner Natasha Jaques 378 8 0 17 Apr 2025
Improving Environment Novelty Quantification for Effective Unsupervised Environment DesignNeural Information Processing Systems (NeurIPS), 2025 Jayden Teoh Wenjun Li Pradeep Varakantham 266 4 0 08 Feb 2025
Eurekaverse: Environment Curriculum Generation via Large Language ModelsConference on Robot Learning (CoRL), 2024 William Liang Sam Wang Hung-Ju Wang Osbert Bastani Dinesh Jayaraman Yecheng Jason Ma SyDa 310 4 0 04 Nov 2024
Adversarial Environment Design via Regret-Guided Diffusion ModelsNeural Information Processing Systems (NeurIPS), 2024 Hojun Chung Junseo Lee Minsoo Kim Dohyeong Kim Songhwai Oh 322 6 0 25 Oct 2024
No Regrets: Investigating and Improving Regret Approximations for Curriculum DiscoveryNeural Information Processing Systems (NeurIPS), 2024 Alexander Rutherford Michael Beukman Timon Willi Bruno Lacerda Nick Hawes Jakob Foerster 313 19 0 27 Aug 2024
Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents Sam Earle Julian Togelius 281 1 0 05 Jul 2024
The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design Constantin Ruhdorfer Matteo Bortoletto Anna Penzkofer Andreas Bulling 374 8 0 25 Jun 2024
Scenario-Based Curriculum Generation for Multi-Agent Autonomous Driving Axel Brunnbauer Luigi Berducci P. Priller D. Ničković Radu Grosu 311 3 0 26 Mar 2024
JaxUED: A simple and useable UED library in Jax Samuel Coward Michael Beukman Jakob Foerster 181 8 0 19 Mar 2024
Refining Minimax Regret for Unsupervised Environment Design Michael Beukman Samuel Coward Michael T. Matthews Mattie Fellows Minqi Jiang Michael Dennis Jakob Foerster 283 14 0 19 Feb 2024
Multi-Agent Diagnostics for Robustness via Illuminated DiversityAdaptive Agents and Multi-Agent Systems (AAMAS), 2024 Mikayel Samvelyan Davide Paglieri Minqi Jiang Jack Parker-Holder Tim Rocktaschel AAML 289 5 0 24 Jan 2024
minimax: Efficient Baselines for Autocurricula in JAX Minqi Jiang Michael Dennis Edward Grefenstette Tim Rocktaschel 273 11 0 21 Nov 2023