OmniReset boosts 9x9 Go self-play by resetting games to random mid-game states
mathemagic1an · x · 2026-07-27
A robotics RL trick called OmniReset is applied to 9x9 Go self-play by resetting games into random legal mid-game states before running PPO.
The reported effect is better exploration and stronger performance against existing policies. The post is presented as a concrete training trick that improves sparse-reward self-play without MCTS, teacher data, or reward shaping.
More from Embodied
- NUS builds a soft force sensor that drives actuators without electronics or power — CurieuxExplorer · 2026-07-27
- Chelsea Finn says robot RL is bottlenecked by physical rollout cost, not algorithms — ycombinator · 2026-07-27
- Robot goes to the fridge and fetches a beer — Darpinian · 2026-07-27
- Researchers show digital circuits can be replicated with knitted fabric — mtizard · 2026-07-27
- Local Qwen models power a robot that tests 78 smartphones’ battery life — gappyvalley · 2026-07-27
- TechCrunch says brain-wave signals could be the next unlock for physical AI training — TechCrunch AI · 2026-07-27