Yicheng Luo's Projects
View useful information about your Atom installation.
A library of reinforcement learning components and agents
Markdown editor for Airwave@NJC
ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
Assignment 1 for the CMU 15418 Course
The hackable text editor
Code for my research project, used to generate statistics from lineup data of the NBA
My blog
Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.
Caffe: a fast open framework for deep learning.
[CoRL 2020] COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning
CompILE: Compositional Imitation Learning and Execution (ICML 2019)
CompILE implementation in JAX
Corax: Core RL in JAX
Command line tools to help instructional teams develop, deploy, and debug sophisticated asynchronous graders.
Code for conservative Q-learning
Conservative Q Learning on top of SAC
Introduction to Parallel Programming class code
A benchmark for offline reinforcement learning.
A tiny package for working with D4RL datasets without D4RL.
A place for dash docsets. Includes scipy, numpy, pandas, scikit-learn, scikit-image,...
TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
Official pytorch implementation of the paper "Deep Kernel Transfer in Gaussian Processes for Few-shot Learning"
Modularized Implementation of Deep RL Algorithms in PyTorch
Discontinuous Hamiltonian Monte Carlo in JAX
使用scrapy,redis, mongodb,graphite实现的一个分布式网络爬虫,底层存储mongodb集群,分布式使用redis实现,爬虫状态显示使用graphite实现