This repo contains the repeatability package of the paper "Training Verifiably Robust Agnets Using Set-Based Reinforcement Learning", Wendl et. al, 2024.

SmartPong is a program created by Andrej Karpathy. This program implements reinfocement learning to train an AI to win at the game Pong. SmartPong outputs lines of code to see the efficiency of the AI ...

Abstract: Spacecraft autonomy is a major barrier to increasing the scope, ambition, and affordability of both Earth-based and deep-space missions. Reinforcement learning (RL) offers huge potential in ...

Abstract: Modern industrial automation increasingly depends on distributed networks of autonomous agents, such as autonomous guided vehicles (AGVs) and machine controllers, to manage dynamic ...

For years, Big Tech CEOs have touted visions of AI agents that can autonomously use software applications to complete tasks for people. But take today’s consumer AI agents out for a spin, whether it’s ...