recent posts
Building a denoising autoencoder in JAX and Haiku for better planning with model-based RL
First look at model-based reinforcement learning MBRL
Exploring model-based RL and learning about its challenges firsthand.
Meta-news
Using natural language processing to visualize news coverage.
Proximal policy optimization (PPO)
My notes from learning to implement PPO including trust regions, importance sampling, and other topics.
Physics informed neural networks
Applying techniques based on the dynamics of the function being learned to improve performance on complex systems.