Implementation of Twin Delayed Deep Deterministic Policy Gradient (TD3) for humanoid continuous control in a Unity physics simulation environment using Keras and TensorFlow.
-
Updated
Mar 8, 2026 - C#
#
continuous-control
Here are 2 public repositories matching this topic...
Unity racing with raycast perception, continuous control, and a custom PyTorch SAC agent. Includes selected policy, real gameplay, and reproducible evaluation evidence.
-
Updated
Oct 4, 2026 - C#
Add this topic to your repo
To associate your repository with the continuous-control topic, visit your repo's landing page and select "manage topics."