We introduce Codex, a GPT language model fine-tuned on publicly availabl...
We train a single, goal-conditioned policy that can solve many robotic
m...
We propose a method to predict the sim-to-real transfer performance of R...
We demonstrate that models trained only in simulation can be used to sol...
The purpose of this technical report is two-fold. First of all, it intro...
Deep reinforcement learning (RL) methods generally engage in exploratory...
Linking human whole-body motion and natural language is of great interes...
Linking human motion and natural language is of great interest for the
g...