Many-Shot In-Context Learning

no code implementations • 17 Apr 2024 • Rishabh Agarwal, Avi Singh, Lei M. Zhang, Bernd Bohnet, Luis Rosias, Stephanie Chan, Biao Zhang, Ankesh Anand, Zaheer Abbas, Azade Nova, John D. Co-Reyes, Eric Chu, Feryal Behbahani, Aleksandra Faust, Hugo Larochelle

We find that both Reinforced and Unsupervised ICL can be quite effective in the many-shot regime, particularly on complex reasoning tasks.

Few-Shot Learning In-Context Learning

Learning Robust Real-Time Cultural Transmission without Human Data

no code implementations • 1 Mar 2022 • Cultural General Intelligence Team, Avishkar Bhoopchand, Bethanie Brownfield, Adrian Collister, Agustin Dal Lago, Ashley Edwards, Richard Everett, Alexandre Frechette, Yanko Gitahy Oliveira, Edward Hughes, Kory W. Mathewson, Piermaria Mendolicchio, Julia Pawar, Miruna Pislar, Alex Platonov, Evan Senter, Sukhdeep Singh, Alexander Zacherl, Lei M. Zhang

We provide a method for generating zero-shot, high recall cultural transmission in artificially intelligent agents.

Proving Theorems using Incremental Learning and Hindsight Experience Replay

no code implementations • 20 Dec 2021 • Eser Aygün, Laurent Orseau, Ankit Anand, Xavier Glorot, Vlad Firoiu, Lei M. Zhang, Doina Precup, Shibl Mourad

Traditional automated theorem provers for first-order logic depend on speed-optimized search and many handcrafted heuristics that are designed to work best over a wide range of domains.

Automated Theorem Proving Incremental Learning

Predicting Sim-to-Real Transfer with Probabilistic Dynamics Models

no code implementations • 27 Sep 2020 • Lei M. Zhang, Matthias Plappert, Wojciech Zaremba

We further show that the transfer metric can predict the effect of training setups on policy transfer performance.