DeepTraffic：クラウドソーシングによる深層強化学習のハイパーパラメータ調整で多エージェント高密度交通をナビゲート
DeepTraffic: Crowdsourced Hyperparameter Tuning of Deep Reinforcement Learning Systems for Multi-Agent Dense Traffic Navigation
数千人が参加できる交通シミュレーション競技を構築し、群衆の力で深層Q学習ネットワークのハイパーパラメータ探索を行った結果を分析した論文。
著者: Lex Fridman, Jack Terwilliger, Benedikt Jenik
分類: cs.NE, cs.AI, cs.RO
原文アブストラクト
We present a traffic simulation named DeepTraffic where the planning systems for a subset of the vehicles are handled by a 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 deep Q-learning network 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.
