Jack Parker-Holder

Feryal M. P. Behbahani

CoRR, 2024

Outliers and Calibration Sets have Diminishing Effect on Quantization of Modern LLMs.

[BibT_eX]

[DOI]

CoRR, 2024

Video as the New Language for Real-World Decision Making.

[BibT_eX]

[DOI]

CoRR, 2024

Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts.

[BibT_eX]

[DOI]

Mikayel Samvelyan

Sharath Chandra Raparthy

CoRR, 2024

Position: Video as the New Language for Real-World Decision Making.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Genie: Generative Interactive Environments.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Position: Open-Endedness is Essential for Artificial Superhuman Intelligence.

[BibT_eX]

[DOI]

Edward Hughes

Michael D. Dennis

Feryal M. P. Behbahani

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Multi-Agent Diagnostics for Robustness via Illuminated Diversity.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, 2024

2023

Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2023

Vision-Language Models as a Source of Rewards.

[BibT_eX]

[DOI]

CoRR, 2023

Synthetic Experience Replay.

[BibT_eX]

[DOI]

Cong Lu

CoRR, 2023

Human-Timescale Adaptation in an Open-Ended Task Space.

[BibT_eX]

[DOI]

CoRR, 2023

Synthetic Experience Replay.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design.

[BibT_eX]

[DOI]

Matthew Thomas Jackson

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Human-Timescale Adaptation in an Open-Ended Task Space.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning.

[BibT_eX]

[DOI]

Jakob Nicolaus Foerster

Roberta Raileanu

Tim Rocktäschel

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Stabilizing Unsupervised Environment Design with a Learned Adversary.

[BibT_eX]

[DOI]

Proceedings of the Conference on Lifelong Learning Agents, 2023

The Effectiveness of World Models for Continual Reinforcement Learning.

[BibT_eX]

[DOI]

Samuel Kessler

Mateusz Ostaszewski

Michal Pawel Bortkiewicz

Proceedings of the Conference on Lifelong Learning Agents, 2023

2022

Automated Reinforcement Learning (AutoRL): A Survey and Open Problems.

[BibT_eX]

[DOI]

J. Artif. Intell. Res., 2022

The Surprising Effectiveness of Latent World Models for Continual Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2022

Learning General World Models in a Handful of Reward-Free Deployments.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Grounding Aleatoric Uncertainty for Unsupervised Environment Design.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Evolving Curricula with Regret-Based Environment Design.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers.

[BibT_eX]

[DOI]

Valerii Likhosherstov

Proceedings of the International Conference on Machine Learning, 2022

Revisiting Design Choices in Offline Model Based Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Conference on Lifelong Learning Agents, 2022

Bayesian Generational Population-Based Training.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Automated Machine Learning, 2022

On-the-fly Strategy Adaptation for ad-hoc Agent Coordination.

[BibT_eX]

[DOI]

Jaleh Zand

Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, 2022

Lyapunov Exponents for Diversity in Differentiable Games.

[BibT_eX]

[DOI]

Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, 2022

Towards an Understanding of Default Policies in Multitask Policy Optimization.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Same State, Different Task: Continual Reinforcement Learning without Interference.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Revisiting Design Choices in Model-Based Offline Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, 2021

Graph Kernel Attention Transformers.

[BibT_eX]

[DOI]

Han Lin

Haoxian Chen

CoRR, 2021

Unlocking Pixels for Reinforcement Learning via Implicit Attention.

[BibT_eX]

[DOI]

Deepali Jain

Xingyou Song

Valerii Likhosherstov

CoRR, 2021

Deep Reinforcement Learning with Dynamic Optimism.

[BibT_eX]

[DOI]

CoRR, 2021

ES-ENAS: Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning.

[BibT_eX]

[DOI]

Xingyou Song

CoRR, 2021

Towards tractable optimism in model-based reinforcement learning.

[BibT_eX]

[DOI]

Stephen Roberts

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research.

[BibT_eX]

[DOI]

Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks 1, 2021

Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Tactical Optimism and Pessimism for Deep Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Replay-Guided Adversarial Environment Design.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Insights From the NeurIPS 2021 NetHack Challenge.

[BibT_eX]

[DOI]

Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, 2021

Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

2020

On Optimism in Model-Based Reinforcement Learning.

[BibT_eX]

[DOI]

Stephen Roberts

CoRR, 2020

One-Shot Bayes Opt with Probabilistic Population Based Training.

[BibT_eX]

[DOI]

Vu Nguyen

Stephen Roberts

CoRR, 2020

Effective Diversity in Population Based Reinforcement Learning.

[BibT_eX]

[DOI]

Krzysztof Marcin Choromanski

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits.

[BibT_eX]

[DOI]

Vu Nguyen

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian.

[BibT_eX]

[DOI]

Alexander Peysakhovich

Jakob N. Foerster

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Learning to Score Behaviors for Guided Policy Optimization.

[BibT_eX]

[DOI]

Anna Choromanska

Michael I. Jordan

Proceedings of the 37th International Conference on Machine Learning, 2020

Stochastic Flows and Geometric Optimization on the Orthogonal Group.

[BibT_eX]

[DOI]

David Cheikhi

Jared Davis

Valerii Likhosherstov

Proceedings of the 37th International Conference on Machine Learning, 2020

Ready Policy One: World Building Through Active Learning.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

Practical Nonisotropic Monte Carlo Sampling in High Dimensions via Determinantal Point Processes.

[BibT_eX]

[DOI]

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Reinforcement Learning with Chromatic Networks.

[BibT_eX]

[DOI]

Xingyou Song

CoRR, 2019

Wasserstein Reinforcement Learning.

[BibT_eX]

[DOI]

Michael I. Jordan

CoRR, 2019

Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes.

[BibT_eX]

[DOI]

CoRR, 2019

Adaptive Sample-Efficient Blackbox Optimization via ES-active Subspaces.

[BibT_eX]

[DOI]

CoRR, 2019

When random search is not enough: Sample-Efficient and Noise-Robust Blackbox Optimization of RL Policies.

[BibT_eX]

[DOI]

CoRR, 2019

From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Provably Robust Blackbox Optimization for Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the 3rd Annual Conference on Robot Learning, 2019

2018

Compressing Deep Neural Networks: A New Hashing Pipeline Using Kac's Random Walk Matrices.

[BibT_eX]

[DOI]