Seungjae Ryan Lee's Projects
Useful extra functionality for TensorFlow 2.x maintained by SIG-addons
TF-Agents is a library for Reinforcement Learning in TensorFlow
:alarm_clock: AI workshopdeadline countdowns
Udacity's AI Nanodegree
This is a curated collection of artworks generated with Generative Adversarial Networks (GANs).
A curated list of optimizers for machine learning.
Collection of awesome Call for Papers to submit your Reinforcement Learning papers
List of competitions related to Reinforcement Learning
Just a personal collection of RL courses I would like to take when I am free.
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
High-quality PyTorch 1.0 implementations of widely used Deep RL algorithms.
openai baselines with tensorflow 2.0
Beyond the Imitation Game collaborative benchmark for enormous language models
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
Variant of Cayman Jekyll theme. Has cards in home page.
Python's kwargs, improved.
Python 3 Chess Engine
Offline code judge system for coding interview questions
Run VS Code on a remote server.
Datasets, tools, and benchmarks for representation learning of code.
A Deeper Look at Experience Replay (Zhang and Sutton, 2017)
Princeton SML310 Final Project
Data visualizations of COVID-19
Cramming the training of a (BERT-type) language model into limited compute.
A Python script that calculates how productive the day was.
Syllabus for Deep RL seminar (2019 Q1; Modulabs Flipped School)