Pinned Loading

1. LAPO LAPO Public

   Code for the ICLR 2024 spotlight paper: "Learning to Act without Actions" (introducing Latent Action Policies)

   Python 76 7

2. jax-raytracing jax-raytracing Public

   Raytracing renderer written in Jax, w/ jitting, gpu support, basic materials.

   Jupyter Notebook 2

3. Rainbow Rainbow Public

   Rainbow DQN implementation accompanying the paper "Fast and Data-Efficient Training of Rainbow" which reaches 205.7 median HNS after 10M frames. 🌈

   Python 43 4

4. stablediffusion-interpolation-tools stablediffusion-interpolation-tools Public

   Tools for smoothly interpolating between prompts for Stable Diffusion models

   Jupyter Notebook 58 10

5. multitask-dojo multitask-dojo Public

   Multitask-dojo is a reinforcement learning environment for research on multi-task RL, generalization, and transfer learning.

   Python 1

6. RecipeNet RecipeNet Public

   Training a neural network to improve recipes by adding new and fitting ingredients. Based on the simplified-recipes-1M dataset.

   Jupyter Notebook 35 11