kclary

Adversaries

Code for experiments in A/B Testing in Networks with Adversarial Members

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

coursework_samples

diceroll

hendrix-rubik

Toy Rubik's cube application

kclary.github.io

REU

variability-RL

Code for experiments in Let’s Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments

saliency_maps

Code for building and experimenting on saliency maps for RL agents.

Toybox

The Machine Learning Toybox for testing the behavior of autonomous agents.

kclary/variability-RL

Code for experiments in Let’s Play Again: Variability of Deep Reinforcement Learning Agents in Atari Environments

kclary/Adversaries

Code for experiments in A/B Testing in Networks with Adversarial Members

kclary/baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

kclary/coursework_samples

kclary/diceroll

kclary/hendrix-rubik

Toy Rubik's cube application

kclary/kclary.github.io

kclary/REU

kclary/taxi

kclary/uvm-maple.github.io