Home

Welcome to the Advanced-Tools wiki!

The final report can be found at final report.

Please refer to the sidebar on the right!

The evaluation proposal I submitted and what the final result should look like:

Implement the MLAgents package in Unity on a machine learning agent to enable it to learn ‘bouldering’, on walls of increasing difficulty with different parameters for samples (attempts to reach the top), and compare the times the top of the walls has been reached for each difficulty with the total amount of samples for that difficulty, with different parameter values.

Edit: I spent around 1.5 week on this concept, but I didn't manage to even stabilize the ragdoll so it would stand on its own feet for at least a few seconds. I expect that is because Configurable Joints are not very well documented and are quite a complicated component to begin with. Since figuring out how those joints work is not the point of this course, I decided to come up with a different evaluation proposal:

Implement the MLAgents package in Unity on a Machine Learning agent to enable it to learn to play a minigame: avoiding falling rocks and collecting valuable items, while the level becomes more difficult in terms of (for example) rock count, falling speed, damage & a dynamic environment as different parameter values, and compare the highscores for each unique set oflevel parameters.