Seungjae Ryan Lee's Projects
MineRL Competition for Sample Efficient Reinforcement Learning - Python Package
ML Boilerplate using PyTorch Lightning, Hydra, and Optuna
MLB-YouTube dataset, code and models for fine-grained activity recognition (CVsports 2018)
PyTorch implementation of latent space reinforcement learning for E2E dialog published at NAACL 2019. It is released by Tiancheng Zhao (Tony) from Dialog Research Center, LTI, CMU
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations
Project for Neuromatch Academy: Computational Neuroscience
A hyperparameter optimization framework
Reinforcement learning environments with musculoskeletal models
Helper for NeurIPS 2018 Challenge: AI for Prosthetics
[WIP] Playing Hard Exploration Games by Watching YouTube (Aytar et al., 2018)
Python Code for MAT321: Numerical Methods (Fall 2020)
A library for encrypted, privacy preserving machine learning
Comparing PDF extraction libraries in Python
Python3 boilerplate with Pylint, Pytest, Sphinx, and TravisCI
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).
Deep Learning (with PyTorch)
Explaining Rainbow DQN with PyTorch
Agents for OpenAI Retro Contest
Pytorch 0.4.1 implementation of DQN / DDQN / DuelingDQN / PER / NoisyNet / CategoricalDQN / Rainbow / QRDQN / h-DQN
Reinforcement Learning papers on exploration methods.
A comprehensive guide to create a structured RL repository to accelerate research.
RL starter files in order to immediatly train, visualize and evaluate an agent without writing any line of code
Single Player Street Fighter 3 environment with MAME Toolkit
Performances of Reinforcement Learning Agents