J. Wilder Lavington's repositories
Improved-Policy-Optimization-for-Online-Imitation-Learning
Code accompanying the paper "Improved Policy Optimization for Online Imitation Learning"
Homeworks-in-Matlab
Homework done in Matlab
Homeworks-in-R
Homework done in R
Probabalistic_RL
Various implementations that investigate reinforcement learning as probabilistic inference. Also includes a couple basic RL algorithms for a comparison.
Actor-Critic-Theory
Algorithmic instatiation of some neat RL theory results.
Bayesian_GAN_models
Creation of Generative Adversarial Network for Bootstrapping
Bomark_CSCI2270_FinalProject
sus wang
cluster_scripts
Some scripts to get setup on slurm clusters + ssh tunneling
Masters-Thesis-Research-Project
Research associated to CRISPR-Cas. Completed under Dr. Manuel Lladser at CU boulder
gym
A toolkit for developing and comparing reinforcement learning algorithms.
Homeworks-in-Julia
All homeworks completed in Julia
Homeworks-in-Python
Homework done in Python
Lavington_CSCI2270_FinalProject
Music finder and recomendation system
machine_learning_540_proj_ubc
Machine Learning Course Project
old_web_page
personal web page.
Parallel_computing_final
Contains code for RL as inference, as well as a generative model implementation for cart-pole to display clock-time convergence speed up
stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
TruePatricianMusic
A music finder. It has a catalog of records that you can add to or remove from, and it can recommend music to you based on genre and related artists.
wilderlavington.github.io
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes