← Authors

Jack Parker-Holder

31 papers · 2019–2025 · 8 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (6) 🐝 Cross-Pollinator (3) 🌍 Conference Polyglot (8) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (15) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (12) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ‘₯ Mega-Team (27) πŸ”¬ Deep Specialist (12) πŸ† Keyword Champion ⚑ Prolific Year (8) πŸ’Ž Century Club (31) πŸ”₯ Unstoppable (7) πŸ—ƒοΈ Keyword Collector (112)

Conferences

NIPS (12) ICML (10) ICLR (3) AISTATS (2) AAAI (1) AUTOML (1) CORL (1) UAI (1)

Top co-authors

Aldo Pacchiano (12) Tim RocktΓ€schel (10) Krzysztof Choromanski (7) Jakob Foerster (6) Minqi Jiang (6) Philip Ball (6) Stephen J. Roberts (5) Yunhao Tang (4) Edward Grefenstette (4) Cong Lu (4)

Keywords

reinforcement learning (11) curriculum learning (4) world model (3) model-based reinforcement learning (3) deep reinforcement learning (3) sample efficiency (3) policy gradient (3) hyperparameter optimization (3) blackbox optimization (3) continuous control (3) policy optimization (3) evolutionary algorithm (2) zero-shot generalization (2) adversarial learning (2) unsupervised environment design (2) active learning (2) offline reinforcement learning (2) attention mechanism (2) data augmentation (2) multi-armed bandit (2)

Papers

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ICLR 2025
Position: Open-Endedness is Essential for Artificial Superhuman Intelligence ICML 2024
Position: Video as the New Language for Real-World Decision Making ICML 2024
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts NIPS 2024
Genie: Generative Interactive Environments ICML 2024
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning ICLR 2023
Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design NIPS 2023
Human-Timescale Adaptation in an Open-Ended Task Space ICML 2023
Synthetic Experience Replay NIPS 2023
Towards an Understanding of Default Policies in Multitask Policy Optimization AISTATS 2022
Evolving Curricula with Regret-Based Environment Design ICML 2022
Learning General World Models in a Handful of Reward-Free Deployments NIPS 2022
Grounding Aleatoric Uncertainty for Unsupervised Environment Design NIPS 2022
Bayesian Generational Population-Based Training AUTOML 2022
From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers ICML 2022
Same State, Different Task: Continual Reinforcement Learning without Interference AAAI 2022
Revisiting Design Choices in Offline Model Based Reinforcement Learning ICLR 2022
Tactical Optimism and Pessimism for Deep Reinforcement Learning NIPS 2021
Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment ICML 2021
Towards tractable optimism in model-based reinforcement learning UAI 2021
Replay-Guided Adversarial Environment Design NIPS 2021
Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL NIPS 2021
Practical Nonisotropic Monte Carlo Sampling in High Dimensions via Determinantal Point Processes AISTATS 2020
Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian NIPS 2020
Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits NIPS 2020
Effective Diversity in Population Based Reinforcement Learning NIPS 2020
Ready Policy One: World Building Through Active Learning ICML 2020
Stochastic Flows and Geometric Optimization on the Orthogonal Group ICML 2020
Learning to Score Behaviors for Guided Policy Optimization ICML 2020
From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization NIPS 2019
Provably Robust Blackbox Optimization for Reinforcement Learning CORL 2019