Ge Yang

ml-logger. A logger, server and visualization dashboard for ML projects

deep-auto-punctuation. a pytorch implementation of auto-punctuation learned character by character

deep_learning_notes. a collection of my notes on deep learning

grammar_variational_autoencoder. pytorch implementation of grammar variational autoencoder

plan2vec. Public Release of Plan2vec Implementation in pyTorch

char2wav_pytorch. pytorch implementation of lyre.ai's char2wav model

gym-fetch. A collection of manipulation tasks with the fetch robot

unitree-go1-setup-guide. Setup guide for the UniTree Go1 robot

params-proto. params_proto, a collection of decorators that makes shell argument passing declarative

deep_learning_papers_TLDR. repository for my TLDR for deep learning papers (and SML papers!)

e-maml. E-MAML, and RL-MAML baseline implemented in Tensorflow v1

react-prosemirror. JavaScript

deep_learning_plotting_example. Some of the plotting code used in our paper, as an example for good-looking plots.

variational_autoencoder_pytorch. pyTorch variational autoencoder, with explainations

ffn. Public Repo for the paper "Overcoming The Spectral-Bias of Neural Value Approximation"

jaynes. Python

nanoGPT. Adapted version of nanoGPT for teaching

react-docgen-loader. a small webpack loader that generates react component metaData using react-docgen

gym-dmc. DeepMind Control Suite plugin for gym

zaku. Machine Learning Job Queue and Procedural Calls

torch-ppo. PyTorch implementation of PPO, A2C, ACKTR, and GAIL

gym-distracting-control. this is a packaged version of the distracting control suite from Stone et al.

practical-rl-at-scale. example for running RL code bases at scale

gym-sawyer. Sawyer robot adapter for OpenAI gym

yatta. yatta is a cli tool that manages a local *.bib index for your PDFs.

visdom_helper. helpers for pyTorch and visdom to better impedance match.

legged-control-suite. A collection of legged robot environments built off DeepMind control

ml-logger_examples. Usages Examples for ML-Logger

reinforcement_learning_learning_notes. Python

waterbear. Waterbear is a simple utility that makes your python dictionary accessible via dot notation.

KL_divergence. small example demonstrating the difference between KL(P||Q) vs KL(Q||P)

tensorflow_data_loading. A list of data loading patterns for TensorFlow

ml-research-containers. A list of community maintained docker images for deep reinforcement learning research

vuer-ts. TypeScript

UnitreecameraSDK_ge. Unitree GO1 camera SDK, forked by Ge Yang

moleskin. A Debugging and console print utility for python

deep_machine_translation. A sequence to sequence model implemented in pyTorch

savio-starter-kit. starter-kit for running stuff on the Berkeley Research Cluster Savio cluster Batteries Included!:battery:

Computer-Vision-Projects. EECS 504- Winter 20

memory. Collection of Replay Buffers for Reinforcement Learning Research

torch_helpers. A collection of helpers for pyTorch

megadraft-demo. JavaScript

react-es6-template. a minimal react es6 template with automatic document generation

rl-playground. Collection of RL algorithm implementations and baselines

tf_logger. logging utility for tensorboard

rl-playground-old. playground repo for rl algorithms