devkumarhf/ur7e-sac-line-following
Reinforcement Learning • Updated • 1
Frozen SAC robot policy, live browser inference and a reproducible CPU benchmark, with source provenance and explicit validation limits.
Note Frozen trained policy, portable NumPy inference and 600-episode CPU evaluation. Kinematic simulation only.
Run a frozen SAC robot policy locally and compare DLS.
Note Run the real exported actor locally in your browser and compare a classical DLS controller.