1 code implementation • 27 Feb 2024 • Kevin Frans, Seohong Park, Pieter Abbeel, Sergey Levine
Can we pre-train a generalist agent from a large amount of unlabeled offline trajectories such that it can be immediately adapted to any new downstream tasks in a zero-shot manner?
no code implementations • 23 Nov 2022 • Kevin Frans, Phillip Isola
Within Powderworld, two motivating challenges distributions are presented, one for world-modelling and one for reinforcement learning.
2 code implementations • 28 Jun 2021 • Kevin Frans, L. B. Soros, Olaf Witkowski
This work presents CLIPDraw, an algorithm that synthesizes novel drawings based on natural language input.
no code implementations • 16 Jun 2021 • Kevin Frans, L. B. Soros, Olaf Witkowski
Inspired by natural evolution, evolutionary search algorithms have proven remarkably capable due to their dual abilities to radiantly explore through diverse populations and to converge to adaptive pressures.
no code implementations • 11 Mar 2021 • Kevin Frans, Olaf Witkowski
Meta-learning models, or models that learn to learn, have been a long-desired target for their ability to quickly solve new tasks.
1 code implementation • 21 Sep 2018 • Kevin Frans, Chin-Yi Cheng
Encoding images as a series of high-level constructs, such as brush strokes or discrete shapes, can often be key to both human and machine understanding.
3 code implementations • ICLR 2018 • Kevin Frans, Jonathan Ho, Xi Chen, Pieter Abbeel, John Schulman
We develop a metalearning approach for learning hierarchically structured policies, improving sample efficiency on unseen tasks through the use of shared primitives---policies that are executed for large numbers of timesteps.
no code implementations • 28 Apr 2017 • Kevin Frans
When creating digital art, coloring and shading are often time consuming tasks that follow the same general patterns.