Selected Publications

This page shares some of my favorite papers, grouped into themes. See my Google Scholar for an up-to-date, comprehensive list.

World Models

World and Human Action Models towards gameplay ideation
A Kanervisto, …, T Pearce, …, K Hofmann
Nature 2024
Paper

Diffusion for World Modeling: Visual Details Matter in Atari
E Alonso*, A Jelley*, V Micheli, A Kanervisto, A Storkey, T Pearce*, F Fleuret*
NeurIPS 2024
Paper | Code

What Do Latent Action Models Actually Learn?
C Zhang*, T Pearce*, P Zhang, K Wang, X Chen, W Shen, L Zhao, J Bian
NeurIPS 2025
Paper

Mineworld: A Real-Time and Open-Source Interactive World Model on Minecraft
J Guo, Y Ye, T He, H Wu, Y Jiang, T Pearce, J Bian
ArXiv 2025
Paper

Imitation Learning

Imitating Human Behaviour with Diffusion Models
T Pearce, T Rashid, A Kanervisto, D Bignell, M Sun, R Georgescu, SV Macua, SZ Tan, I Momennejad, K Hofmann, S Devlin
ICLR 2023
Paper | Code

Counter-Strike Deathmatch with Large-Scale Behavioural Cloning
T Pearce, J Zhu
IEEE Conference on Games 2022, Best Paper Award
Paper | Video Intro | Code

C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory
T Luo, T Pearce, H Chen, J Chen, J Zhu
NeurIPS 2024
Paper

Scaling Laws

Reconciling Kaplan and Chinchilla Scaling Laws
T Pearce, J Song
TMLR 2024
Paper | Code

Scaling Laws for Pre-training Agents and World Models
T Pearce*, T Rashid*, D Bignell, R Georgescu, S Devlin, K Hofmann
ICML 2025
Paper

Reinforcement Learning

TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play
F Lin*, S Huang*, T Pearce, W Chen, W-W Tu
AAMAS 2023
Paper

Uncertainty and Neural Networks

Censored Quantile Regression Neural Networks
T Pearce, JH Jeong, Y Jia, J Zhu
NeurIPS 2022
Paper | Code

Understanding Softmax Confidence and Uncertainty
T Pearce, A Brintrup, J Zhu
ArXiv 2021
Paper

Avoiding Kernel Fixed Points: Computing with ELU and GELU Infinite Networks
R Tsuchida, T Pearce, C Van Der Heide, F Roosta, M Gallagher
AAAI 2021
Paper

Uncertainty in Neural Networks: Approximately Bayesian Ensembling
T Pearce, F Leibfried, M Zaki, A Brintrup, A Neely
AISTATS 2021
Paper | Video Intro | Interactive Demo | Code

Expressive Priors in Bayesian Neural Networks: Kernel Combinations and Periodic Functions
T Pearce, R Tsuchida, M Zaki, A Brintrup, A Neely
UAI 2019
Paper | Video Intro | Code

High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach
T Pearce, M Zaki, A Brintrup, A Neely
ICML 2018
Paper | Video Intro | Code