潜在空間強化学習によるステアリング角予測
Latent Space Reinforcement Learning for Steering Angle Prediction
高忠実度シミュレータ内で、画像から低次元の潜在表現を抽出し、強化学習で車のステアリング角を予測するモジュール型手法を提案した。
著者: Qadeer Khan, Torsten Schön, Patrick Wenzel
分類: cs.LG, cs.AI, cs.CV, cs.RO, stat.ML
原文アブストラクト
Model-free reinforcement learning has recently been shown to successfully learn navigation policies from raw sensor data. In this work, we address the problem of learning driving policies for an autonomous agent in a high-fidelity simulator. Building upon recent research that applies deep reinforcement learning to navigation problems, we present a modular deep reinforcement learning approach to predict the steering angle of the car from raw images. The first module extracts a low-dimensional latent semantic representation of the image. The control module trained with reinforcement learning takes the latent vector as input to predict the correct steering angle. The experimental results have showed that our method is capable of learning to maneuver the car without any human control signals.
