가입 후 초대 링크를 공유하면 동영상 재생 및 초대 보상을 받을 수 있습니다.

Induction Labs
@induction_labs
가입 August 2025
2 팔로잉 중    4.7K 팬
Intrinsic discovery uses RL to uncover new behavior in an environment. The model is rewarded for reaching states unlike those found so far, then sampled again after each update to push exploration further. This approach discovers 5× more novel states than a frozen baseline.
더 보기