Bipedal Machine Learning Walker
Machine Learning · Ongoing
- Role
- Independent Researcher
- Timeline
- Aug 2026 – Present
- Team
- Solo project
- Tools
- Python, Reinforcement Learning
Training a pre-defined bipedal model to walk across a virtual environment by designing and iterating on reward functions.
The Problem
I wanted real intuition for how machine learning works, past just following tutorials. Reinforcement learning felt like the right starting point, since you can see success or failure immediately.
My Approach
I'm training a pre-defined bipedal model to walk through a virtual environment by defining and iterating on reward functions. It's a solo project, and I'm treating it as ongoing learning rather than a single deliverable.
Outcome
Still in development. I've got more planned over the next year as I extend what the model can do and refine the reward design.
