Hanjun Yoo retweeted
We trained an imaginative agent! โจ
Agima: an omni agent that plans by imagining futures.
๐ฆ๐๐ง: Directly generalizes to harder tasks! ๐ฎ%โ๐ฐ๐ฌ%, beats GPT-5.6 Sol (๐ฎ๐ฌ%).
๐ฅ๐: New ways to imagine emerge! Imagines a second plan only if the first one fails (๐ฏ๐ฎ%โ๐ญ๐ฌ๐ฌ%).
Agima: an omni agent that plans by imagining futures.
๐ฆ๐๐ง: Directly generalizes to harder tasks! ๐ฎ%โ๐ฐ๐ฌ%, beats GPT-5.6 Sol (๐ฎ๐ฌ%).
๐ฅ๐: New ways to imagine emerge! Imagines a second plan only if the first one fails (๐ฏ๐ฎ%โ๐ญ๐ฌ๐ฌ%).
16
60
356
44,903
Hanjun Yoo retweeted
Our paper RATs has been selected as CoRL spotlight!
We apply "sleep time scaling" to agentic robotics learning. The agent aquires skills during play and then uses these skills at test time. Check out our project page at : playful-rats.github.io @junyi42
We apply "sleep time scaling" to agentic robotics learning. The agent aquires skills during play and then uses these skills at test time. Check out our project page at : playful-rats.github.io @junyi42
Excited to release our new work: Playful Agentic Robot Learning w/ @junyi42!
Instead of relying on test-time scaling, we found that a "pretraining stage" through curious play enables robots to discover general skills before any tasks are assigned.
๐ playful-rats.github.io
5
9
66
6,448
Hanjun Yoo retweeted
Children learn from play. Can robots do the same?
We propose ๐๐ฅ๐๐ฒ๐๐ฎ๐ฅ ๐๐ ๐๐ง๐ญ๐ข๐ ๐๐จ๐๐จ๐ญ ๐๐๐๐ซ๐ง๐ข๐ง๐ , a paradigm that gives embodied coding agents a play stage before downstream tasks arrive, and instantiate it with ๐๐๐๐ฌ (Robotics Agent Teams), where robots s through curious play.
Co-led with @jiaxin_ge_
We propose ๐๐ฅ๐๐ฒ๐๐ฎ๐ฅ ๐๐ ๐๐ง๐ญ๐ข๐ ๐๐จ๐๐จ๐ญ ๐๐๐๐ซ๐ง๐ข๐ง๐ , a paradigm that gives embodied coding agents a play stage before downstream tasks arrive, and instantiate it with ๐๐๐๐ฌ (Robotics Agent Teams), where robots s through curious play.
Co-led with @jiaxin_ge_
10
64
351
98,415