Yicheng Luo's Projects
iTerm integration with Emacs
Jam - JAX models
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Jax (Flax) implementation of algorithms for Deep Reinforcement Learning with continuous action spaces.
Beautifier for javascript
JavaScript Fireworks, Chrome Experiment
从零开始的 JSON 库教程
Gymnasium for offline reinforcement learning
Kalman Filter book using Jupyter Notebook. Focuses on building intuition and experience, not formal proofs. Includes Kalman filters,extended Kalman filters, unscented Kalman filters, particle filters, and more. All exercises include solutions.
Official implementation of NeurIPS 2021 paper: "Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation". This repo contains a copy of the code for "Universal Humanoid Controller" and "Kinematic Policy".
Kalman Variational Auto-Encoder
Left is a clean, whitespace-happy layout for Jekyll.
A directory of local support services and volunteer opportunities
Luigi is a Python module that helps you build complex pipelines of batch jobs. It handles dependency resolution, workflow management, visualization etc. It also comes with Hadoop support built in.
LXM3: XManager launch backend for HPC clusters
Reinforcement learning library in JAX.
Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.
A pytorch reprelication of the model-based reinforcement learning algorithm MBPO
Library for Model Based RL
A high-level Condor DAGMan Scheduler in Scala/Java
A collection of MuJoCo based environments.
A Multi-Task Dataset for Simulated Humanoid Control
Cached copy of mortardata/mortar-luigi from before it was taken down.
MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.
The NBA's stats API for the browser or Node