Image de couverture de livre

Refining Minimax Regret for Unsupervised Environment Design

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Beukman, Michael, Coward, Samuel, Matthews, Michael, Fellows, Mattie, Jiang, Minqi, Dennis, Michael, Foerster, Jakob
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

JaxUED: A simple and useable UED library in Jax
par: Coward, Samuel, et autres
Publié: (2024)

Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks
par: Matthews, Michael, et autres
Publié: (2024)

No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
par: Rutherford, Alexander, et autres
Publié: (2024)

SOReL and TOReL: Two Methods for Fully Offline Reinforcement Learning
par: Fellows, Mattie, et autres
Publié: (2025)

Learning to Reason at the Frontier of Learnability
par: Foster, Thomas, et autres
Publié: (2025)

Goal-Conditioned Agents that Learn Everything All at Once
par: Matthews, Michael, et autres
Publié: (2026)

Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning
par: Matthews, Michael, et autres
Publié: (2024)

JaxLife: An Open-Ended Agentic Simulator
par: Lu, Chris, et autres
Publié: (2024)

An Optimisation Framework for Unsupervised Environment Design
par: Monette, Nathan, et autres
Publié: (2025)

DéjàQ: Open-Ended Evolution of Diverse, Learnable and Verifiable Problems
par: Röpke, Willem, et autres
Publié: (2026)

minimax: Efficient Baselines for Autocurricula in JAX
par: Jiang, Minqi, et autres
Publié: (2023)

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments
par: Beukman, Michael, et autres
Publié: (2026)

Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs
par: Furelos-Blanco, Daniel, et autres
Publié: (2025)

Hierarchical Behaviour Spaces
par: Matthews, Michael Tryfan, et autres
Publié: (2026)

Improving Regret Approximation for Unsupervised Dynamic Environment Generation
par: Mead, Harry, et autres
Publié: (2026)

Scalable Option Learning in High-Throughput Environments
par: Henaff, Mikael, et autres
Publié: (2025)

Policy-Guided Diffusion
par: Jackson, Matthew Thomas, et autres
Publié: (2024)

Learning Multi-Agent Communication with Contrastive Learning
par: Lo, Yat Long, et autres
Publié: (2023)

Learning to Act without Actions
par: Schmidt, Dominik, et autres
Publié: (2023)

Adversarial Environment Design via Regret-Guided Diffusion Models
par: Chung, Hojun, et autres
Publié: (2024)

TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design
par: Cho, Geonwoo, et autres
Publié: (2025)

Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs
par: Boudart, Pierre, et autres
Publié: (2026)

The Yokai Learning Environment: Tracking Beliefs Over Space and Time
par: Ruhdorfer, Constantin, et autres
Publié: (2025)

High entropy leads to symmetry equivariant policies in Dec-POMDPs
par: Forkel, Johannes, et autres
Publié: (2025)

Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds
par: Huang, Jiayi, et autres
Publié: (2023)

Mixture of Experts in a Mixture of RL settings
par: Willi, Timon, et autres
Publié: (2024)

Simplifying Deep Temporal Difference Learning
par: Gallici, Matteo, et autres
Publié: (2024)

The Generalization Gap in Offline Reinforcement Learning
par: Mediratta, Ishita, et autres
Publié: (2023)

The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning
par: Sims, Anya, et autres
Publié: (2024)

Mirror Learning: A Unifying Framework of Policy Optimisation
par: Kuba, Jakub Grudzien, et autres
Publié: (2022)

Evolution Strategies at the Hyperscale
par: Sarkar, Bidipta, et autres
Publié: (2025)

Symmetry-Breaking Augmentations for Ad Hoc Teamwork
par: Hammond, Ravi, et autres
Publié: (2024)

Abstraction for Offline Goal-Conditioned Reinforcement Learning
par: Wibault, Clarisse, et autres
Publié: (2026)

Graph Persistence goes Spectral
par: Ji, Mattie, et autres
Publié: (2025)

Refining Filter Global Feature Weighting for Fully-Unsupervised Clustering
par: Galis, Fabian, et autres
Publié: (2025)

Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps
par: Ellis, Benjamin, et autres
Publié: (2024)

Rethinking Early Stopping: Refine, Then Calibrate
par: Berta, Eugène, et autres
Publié: (2025)

Behaviour Distillation
par: Lupu, Andrei, et autres
Publié: (2024)

DITTO: Offline Imitation Learning with World Models
par: DeMoss, Branton, et autres
Publié: (2023)

Procedural Generation of Algorithm Discovery Tasks in Machine Learning
par: Goldie, Alexander D., et autres
Publié: (2026)