A Type-1 Diabetes simulator implemented in Python for Reinforcement Learning purpose

Learning human driver models from NGSIM data with imitation learning.

Iterative LQG for a couple of MuJoCo models

This is the Reasoning and Learning Lab participation to The Conversational Intelligence Challenge - NIPS 2017 Live Competition (http://convai.io/)

Reinforcement learning algorithms for Oregon State University's bipedal robot, Cassie

Angular Dashboard to edit neural networks, launch supervised/rl experiments and track them.

Reinforcement learning analysis using Python, OpenAI Gym and rllab.