Nicolas Porcel

Learning to Play No-Press Diplomacy with Best Response Policy Iteration pdf

Tom Eccles, Satinder Singh, Julien P'erolat, 2020, NeurIPS.

Alchemy: A structured task distribution for meta-reinforcement learning pdf

Zeb Kurth-Nelson, Demis Hassabis, Matthew Botvinick, 2021, ArXiv.

Open-Ended Learning Leads to Generally Capable Agents pdf

Max Jaderberg, Valentin Dalibard, Adam Stooke, 2021, ArXiv.

Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents

Zeb Kurth-Nelson, Demis Hassabis, Matthew Botvinick, 2021, NeurIPS Datasets and Benchmarks.