David Bignell — accepted AI-conference papers

2025

Scaling Laws for Pre-training Agents and World Models

Tim Pearce, Tabish Rashid, David Bignell, Raluca Georgescu, Sam Devlin, Katja Hofmann

ICML 2025poster

The performance of embodied agents has been shown to improve by increasing model parameters, dataset size, and compute. This has been demonstrated in domains from robotics to video games, when generative learning objectives on offline datasets (pre-training) are used to model an agent's behavior (im…

Cited by 5 Source ↗PDF ↗Scholar ↗

2022

Uni[MASK]: Unified Inference in Sequential Decision Problems

Micah Carroll, Orr Paradise, Jessy Lin, Raluca Georgescu, Mingfei Sun, David Bignell +5

NeurIPS 2022accept

Randomly masking and predicting word tokens has been a successful approach in pre-training language models for a variety of downstream tasks. In this work, we observe that the same idea also applies naturally to sequential decision making, where many well-studied tasks like behavior cloning, offline…

Cited by 37 Source ↗PDF ↗code ↗Scholar ↗