Pinned Repositories
ADHD-ACE
AI
API-In-Table
batch_rl
Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games
CQL
Code for conservative Q-learning
CS285hw
fs-keeper
github-slideshow
A robot powered training repository :robot:
Keeper-App
seg2vid
Video Generation from Single Semantic Label Map
relmelegy's Repositories
relmelegy/seg2vid
Video Generation from Single Semantic Label Map
relmelegy/ADHD-ACE
relmelegy/AI
relmelegy/API-In-Table
relmelegy/batch_rl
Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games
relmelegy/CQL
Code for conservative Q-learning
relmelegy/CS285hw
relmelegy/fs-keeper
relmelegy/github-slideshow
A robot powered training repository :robot:
relmelegy/Keeper-App
relmelegy/metisfl
MetisFL is a federated learning framework that allows developers to easily federate their machine learning workflows and train their models across distributed data silos without ever collecting the data in a centralized location. The core of the framework is written in C++ and focuses on scalability, speed and resiliency.
relmelegy/modulus-sym
An abstracted framework for training AI surrogates of physical systems using physics-based symbolic loss functions
relmelegy/pacman-game
SMC Computer Science Club pacman game
relmelegy/ray
An open source framework that provides a simple, universal API for building distributed applications. Ray is packaged with RLlib, a scalable reinforcement learning library, and Tune, a scalable hyperparameter tuning library.
relmelegy/QR-Code
relmelegy/rlkit
Collection of reinforcement learning algorithms
relmelegy/search_for_letters_webapp
This simple webapp searches for letters in a phrase and saves the results to a SQL database
relmelegy/Sketch-to-Video
Final project for Applied Computer Vision -- Columbia University
relmelegy/smc-comsci
Computer Science Club at SMC
relmelegy/smc_ags_newsletter
smc ags newsletter project
relmelegy/stylegan
relmelegy/Tic-Tac-Toe-JavaScript
SMC CS Club Tic Tac Toe game written in JavaScript!