research
∙
06/07/2023
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
Foundation models are first pre-trained on vast unsupervised datasets an...
share
research
∙
11/18/2022
Building a Subspace of Policies for Scalable Continual Learning
The ability to continuously acquire new knowledge and skills is crucial ...
research
∙
10/15/2021
SaLinA: Sequential Learning of Agents
SaLinA is a simple library that makes implementing complex sequential le...
research
∙
10/11/2021