データ拡張とモデルベース強化学習による実世界迷路ゲームの高効率学習
Sample-Efficient Learning to Solve a Real-World Labyrinth Game Using Data-Augmented Model-Based Reinforcement Learning
カメラ画像から低次元観測と迷路の位置周辺の切り出し画像を抽出し、実機上でのモデルベース強化学習と対称性を利用したデータ拡張により、5時間の実世界訓練データだけで実物の迷路ゲームを解く制御方策を学習した。
著者: Thomas Bi, Raffaello D'Andrea
分類: cs.RO, cs.AI
原文アブストラクト
Motivated by the challenge of achieving rapid learning in physical environments, this paper presents the development and training of a robotic system designed to navigate and solve a labyrinth game using model-based reinforcement learning techniques. The method involves extracting low-dimensional observations from camera images, along with a cropped and rectified image patch centered on the current position within the labyrinth, providing valuable information about the labyrinth layout. The learning of a control policy is performed purely on the physical system using model-based reinforcement learning, where the progress along the labyrinth's path serves as a reward signal. Additionally, we exploit the system's inherent symmetries to augment the training data. Consequently, our approach learns to successfully solve a popular real-world labyrinth game in record time, with only 5 hours of real-world training data.
