HARBOR trains robot locomotion policies from a single prompt, fully autonomously in 1.5 hours
breadli428 · x · 2026-09-05
HARBOR autonomously handles the entire robot policy training loop: from one prompt, it builds the task, designs rewards, trains, tunes, and evaluates a locomotion policy in simulation — end to end in about 1.5 hours. The work has been accepted at CoRL 2026, showing how far agent-driven RL training has come.
More from coding & agent
- tldraw reuses its record-diff system to power its animation engine with almost no plumbing — max__drake · 2026-09-05
- Animations are just diff replays: tldraw flash lets you drag shapes mid-animation — max__drake · 2026-09-05
- tldraw flash launches next week: canvas changes are tracked as record diffs, the system agents keep tripping over — max__drake · 2026-09-05
- Databricks exec: AI coding is a duopoly today, open-source models will make it a triopoly — Yuchenj_UW · 2026-09-05
- The folder is the agent: how one engineer sustainably runs 44 specialized AI agents — danshipper · 2026-09-05
- ffmpeg-skill turns coding agents into local video editors with a probe-edit-verify workflow — TheMoonMidas · 2026-09-05