💻 Unity 2024 ML-Agents | Live AI Robot Training | Kyle 2a0a | PyTorch | Part 19

Channel:

p3nGu1nZz

Subscribers:

375

Published on January 24, 2024 7:06:36 PM ● Video Link: https://www.youtube.com/watch?v=jvmuaEytLnY

Duration: 2:11:05

25 views

0

In this video, I will show you how to train a robotic walker to cooperate with other walkers in a hostile environment using Unity Machine Learning Agents Toolkit.

**Simulating** Kyle.a0a-170m on the same column training environment, but now with improved settings to the respawn timer of the yellow target sphere. Kyle also seems to be improving pushing off from the walls. I also decided to set the wall touching reward to -1, so that it matches any bone which has contact with the ground as -1 too. This will encourage Kyle to keep away from the walls as they punish him, and who likes that right?

------
you can find the latest kyle models on our github ::
https://github.com/cat-game-research/NekoCatGame/tree/main/RagdollTrainer/results
------

If you enjoyed this video, please hit the like button and subscribe to my channel for more Unity Machine Learning content. And don’t forget to leave a comment below and let me know what you think of my robotic walker game. Thanks for watching!

#unity #gamedev #ai #mlagents #robot #walker #physics #2023 #visualstudio