Machine Learning

DeepTraffic: Driving Fast through Dense Traffic with Deep Reinforcement Learning

This topic contains 0 replies, has 1 voice, and was last updated by  arXiv 11 months ago.


  • arXiv
    5 pts

    DeepTraffic: Driving Fast through Dense Traffic with Deep Reinforcement Learning

    We present 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 primary goal of DeepTraffic is to make the hands-on study of deep reinforcement learning accessible to thousands of students, educators, and researchers in order to inspire and fuel the exploration and evaluation of DQN variants and hyperparameter configurations through large-scale, open competition. This paper 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.

    DeepTraffic: Driving Fast through Dense Traffic with Deep Reinforcement Learning
    by Lex Fridman, Benedikt Jenik, Jack Terwilliger
    https://arxiv.org/pdf/1801.02805v1.pdf

You must be logged in to reply to this topic.