← Discover more

My Highlights

FFFF00-FF48D3 · https://highlighterai.com/welcome Public

by @PulFaire

Join to follow
@PulFaire 1 highlight
1/1

Our experiments are conducted in an unsupervised goal-conditioned setting, where no demonstrations or rewards are provided, so an agent must explore (from scratch) and learn how to maximize the likelihood of reaching commanded goals.

1 234

Start highlighting

Join HighlighterAI to save and share your own highlights.

Join