Josh Achiam

cpo. Constrained Policy Optimization

rl-intro. TeX

optimization-notes. Review notes for EE127/227A, based on the Spring 2017 iteration of the course.

surprise. Surprise-based intrinsic motivation for deep reinforcement learning

rnn-playground. Playground for some RNN stuff in Torch.

tak-ai. An open-source implementation of the game Tak (of The Kingkiller Chronicle) and an AI for it.

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

spinningup. An educational resource to help anyone learn deep reinforcement learning.

jachiam.github.io. Aspirationally: A minimalist webpage + blog. Most likely outcome: nothing! Fun either way. :)