Chuying Li (@Sinclair4o4err) | teapawt

Chuying Li retweeted

@haoqik322Sep 21

6/ 📄 Paper: arxiv.org/abs/2609.19801 Huge thanks to @YimingZhang_33, @gyyyyy710, @Sinclair4o4err, @jiseshen, @XTRose88, @koe_ye40329, and @Lianhuiq for making this work possible! 🙌 And special thanks to @zhaoyk729 for helping with the demo! 🎬 We’re excited about what adaptive environments can unlock for embodied RSI!

DeliveryGym: An RL Environment for Long-Horizon Embodied Agent...

Executable environments enable LLM agents to learn from the consequences of their actions. For embodied agents, those consequences extend beyond whether the current task succeeds: completing a...

11

369