Hacker News new | comments | show | ask | jobs | submit login

Who's ready for some "Deep Pimping"?


ABSTRACT: We explore the adage "pimpin' ain't easy" in the context of deep reinforcement learning in the OpenAI environment GTAV. We train a Deep Q-Network (DQN) to optimize player cash flows. Over the course of training, our network learns to keep these hoes in line, and discipline misbehaving customers.

Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact