π¨βπ» I'm Jacob Pettit, and I work on reinforcement learning research. My GitHub account houses my personal projects.
I also blog at Welcome to My Brain and at The Merge.
- π€ Multiagent RL. Both collaborative and competitive.
- πͺ Robust RL. Can we make RL handle changes in its environment, such as noise in observations and in environment dynamics?
- 𧬠Sequence optimization. Think DNA/RNA/amino acid optimization and mathematical expression optimization.
- π mRNA vaccines (and the COVID vaccine)!
- π¬ ML for bio
- π¬ Biology - Protein folding, mRNA, and the COVID vaccine! DeepMind's AlphaFold release and the exciting science of the COVID vaccine inspired me to learn more about them.
- π» JavaScript, JAX in Python, and SWE best practices.