Self-supervised Reinforcement Learning
concept
2 mentions
1 recordings
first heard Jan 2026
last heard 2 Jan
↓2 vs the 6 months before
Approach that learns representations without explicit rewards
Trend
No mentions in the last 6M.Widen the range to see when Self-supervised Reinforcement Learning was said.
Moments
newest first · ▶ plays the momentKevin WangLatent Space: The AI Engineer Podcast · [NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised... · 5:07 · 2 Jan
…So can self-supervised RL scale in similar ways?…
Kevin WangLatent Space: The AI Engineer Podcast · [NeurIPS Best Paper] 1000 Layer Networks for Self-Supervised... · 4:37 · 2 Jan
…So we tried a different approach to RL, um, called self-supervised RL, where instead of learning like a value function, we're learning representations of states, actions, and future states, such that the representations along the same trajectory are pushed together, the representations.…
All 2 moments