Ryan Sullivan

Syllabus. Synchronized Curriculum Learning for RL Agents

reward-surfaces. Python

PPO-v3. Adding Dreamer-v3's implementation tricks to CleanRL's PPO

PillAR. AR Pill tracking app

SNNsim. A simulator of the Loihi architecture for testing Spiking Neural Network performance.

AlphaSmash. Using AlphaRank to rank professional Super Smash Bros Melee competitors

Thought-Cloning-CT. Fork of Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

PufferLib. Simplifying reinforcement learning for complex game environments

ParksAndWreck. A fun car parking game built at BoilerMake V