Get Started with ML-Agents in Unity - Part 6: Inference & Training Stats

In the final part of the series, we load our trained Turtle Agent into Unity, visualize training stats with TensorBoard, and set up a custom config file to improve training performance.

📀 Get the completed Unity Project from here:   / project-source-6-127045834  
📜 'Turtle.yaml' config file: https://github.com/LudicWorlds/ml-age...
📜 To run a training session, use these commands: https://github.com/LudicWorlds/ml-age...

← Previous Video • Get Started with ML-Agents in Unity - Part 5: Parallel Training & Feedback:    • Get Started with ML-Agents in Unity -...  

▬ Support My Work ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

❤️ Support me on Patreon:   / ludicworlds  
☕ Buy me a coffee: https://ko-fi.com/ludicworlds

Thank you for your support!


▬ Timestamps ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

0:00 - Intro
0:47 - Terminal Read-out
2:37 - Import ONNX File
3:43 - Set 'Inference Only' Behavior
4:33 - Test Trained Model
4:58 - TensorBoard
6:16 - Config YAML File
8:02 - Set 'Default' Behavior
8:48 - Final Training Run
10:45 - Outro


▬ Useful Links ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

► ML-Agents GitHub: https://github.com/Unity-Technologies...
► ML-Agents Overview: https://unity-technologies.github.io/...
► ML-Agents Docs - Training Configuration File: https://unity-technologies.github.io/...


▬ Credits ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

► Music by - CO.AG Music:    / @co.agmusic  

#unity #ai #mlagents #reinforcementlearning