Week 7 Update

Aarshdeep Singh N -

This week has been a mix of reflection, correction, and continued learning. After reviewing my progress from last week, I realized that I had made a mistake with the parameters in the decision boundary graph I created. I had accidentally used values of +24 and -24 for the pole angle range, which led to incorrect information. The correct values should have been +0.4 and -0.4 for the pole angle range, and this error caused a major issue.

The mistake was significant because the wrong parameters gave me information that was the opposite of what I would have gotten if the angle had been correct. This led to a misunderstanding of the agent’s behavior and the way it interacted with the environment. Once I realized the error, I immediately corrected the parameters and generated a new graph.

With the corrected graph, I can now better understand the decision boundaries and how the agent makes decisions. It’s been an eye-opening experience, as it really highlights the importance of precision when working with machine learning models. A small mistake can lead to a completely different interpretation of the data and affect the overall learning process.

As I continue to collect data and analyze the decision boundary graph, I’m gaining more insight into the model’s behavior. I’m excited to continue refining the model and gaining a deeper understanding of how it works.

Thanks for reading, and I’ll keep you updated with my progress!

More Posts

Comments:

All viewpoints are welcome but profane, threatening, disrespectful, or harassing comments will not be tolerated and are subject to moderation up to, and including, full deletion.

    aashi_h
    Hi Aarsh, I love that you are persevering even through the difficulty of your project. What do you think caused the error to scew off the graph?
    aarshdeep_singh_n
    Hi Aashi, The graph was a little messed up because instead of using the radian function in the code, I set the value to 24 directly, which gave a false sense of security when looking at the graph. It showed prefect results, when in actuality the graph was outside the bounds of the environement

Leave a Reply

Your email address will not be published. Required fields are marked *