ASH learns long-horizon embodied policies from unlabeled internet video via a self-improvement loop that trains an IDM on its own trajectories and extracts supervision plus key-moment memory from video.
Large language models are semi-parametric reinforcement learning agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ASH: Agents that Self-Hone via Embodied Learning
ASH learns long-horizon embodied policies from unlabeled internet video via a self-improvement loop that trains an IDM on its own trajectories and extracts supervision plus key-moment memory from video.