Jack Parker-Holder

Affiliations

University of Oxford

papers

1,079

total citations

papers (14)

Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits

NEURIPS 2020arXiv

citations

Tactical Optimism and Pessimism for Deep Reinforcement Learning

NEURIPS 2021arXiv

citations

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

NEURIPS 2020arXiv

citations

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

NEURIPS 2021arXiv

citations

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design

NEURIPS 2023arXiv

citations

Grounding Aleatoric Uncertainty for Unsupervised Environment Design

NEURIPS 2022arXiv

citations

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

NEURIPS 2022arXiv

citations

Imagined Autocurricula

NEURIPS 2025arXiv

citations

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

ICML 2024

citations

Position: Open-Endedness is Essential for Artificial Superhuman Intelligence

ICML 2024

citations

Jack Parker-Holder

Affiliations

papers (14)

Genie: Generative Interactive Environments

Effective Diversity in Population Based Reinforcement Learning

Replay-Guided Adversarial Environment Design

Synthetic Experience Replay

Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits

Tactical Optimism and Pessimism for Deep Reinforcement Learning

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

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

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design

Grounding Aleatoric Uncertainty for Unsupervised Environment Design

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

Imagined Autocurricula

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

Position: Open-Endedness is Essential for Artificial Superhuman Intelligence

papers (14)

Genie: Generative Interactive Environments

Effective Diversity in Population Based Reinforcement Learning

Replay-Guided Adversarial Environment Design

Synthetic Experience Replay

Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits

Tactical Optimism and Pessimism for Deep Reinforcement Learning

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

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

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design

Grounding Aleatoric Uncertainty for Unsupervised Environment Design

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

Imagined Autocurricula

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

Position: Open-Endedness is Essential for Artificial Superhuman Intelligence