DeepTraffic: Driving Fast through Dense Traffic with Deep Reinforcement Learning

2018-09-27T18:51:31+00:00 January 11th, 2018|AI, NLP, Machine Learning|Comments Off on DeepTraffic: Driving Fast through Dense Traffic with Deep Reinforcement Learning

This paper presents a micro-traffic simulation (named “DeepTraffic”) where the perception, control, and planning systems for one of the cars are all handled by a single neural network as part of a model-free, off-policy reinforcement learning process. The paper also investigates the crowd-sourced hyperparameter tuning of the policy network that resulted from the first iteration of the DeepTraffic competition where thousands of participants actively searched through the hyperparameter space with the objective of their neural network submission to make it onto the top-10 leaderboard.

Click Here to Download Paper

Bitnami