Pinned Loading

1. ALBERTA ALBERTA Public

   Response-aware active learning for sparse expert supervision in Atomic Chess.

   Python

2. mujoco mujoco Public

   Forked from google-deepmind/mujoco

   Fork of google-deepmind/mujoco for J2 plasticity development.

   C++

3. LT-GCPN LT-GCPN Public

   LT-GCPN (Local-Traveller GCPN) is a PPO-trained graph convolutional policy in which a mobile agent repairs lesioned spatial graphs through radius-limited edge edits that restore network dynamics.

   Python