BCHoagland

DARLA

PyTorch implementation of the DARLA reinforcement learning pipeline

Multi-Modal

VINS

Implementation of Value Iteration from Demonstrations with Negative Sampling (VINS) for conservative value function extrapolation

attention-learn-to-route

Attention based model for learning to solve different routing problems

ChaRLes

My personal Deep RL library

latex

my latex files

TDA-Project

Persistent homology and autoencoders

Autoencoders

Implementations of and latent space demonstrations with autoencoders, VAEs, and ß-VAEs in PyTorch

Gandalf

Generative Adversarial Network library, implemented with PyTorch

Glados

RNN for text generation

Sutton-and-Barto

Implementations of the Algorithms in the Sutton and Barto 'Reinforcement Learning - 2nd Ed.' Textbook

Anomaly-Detection

bchoagland.github.io

My website

Conjugate-Gradient

Implementations of iterative methods for solving linear systems

Continuity

Investigating the effects of replacing the typical Bellman backup with the HJB when using imperfect dynamics models

CS-4104

Some implementations of the algorithms discusses and assigned in CS-4104

CyberPatriot

Data-Modeling

Different basic approaches to modeling conditional stochastic datasets

DE-CS-II

Duel Enrollment Computer Science II

disease-sim

Evolution-Strategies

explosive

Full-Q

Experiments with using policy re-parameterization to allow for the full computation of the Q-learning gradient

HackBI

Website for HackBI 2018. Created by Braden Hoagland

HJB-regularized-RL

Iris

Iris personal assistant for the BigParser 2017 Summer Hackathon

MUN-Timer

Custom timer for use when chairing MUN committees

RL-Utils

Generic RL training tools centered around PPO algorithm. Compatible with any OpenAI Gym environment

spell-manager

Transfer-Learning

Implementations of and demonstrations with various transfer learning techniques