インタラクティブリプレイによるロボットナビゲーションのワンショット強化学習
One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay
環境を一度だけ走行して得たデータからインタラクティブな世界モデルを構築し、実環境の変動下でもファインチューニングなしでゼロショット転移できるナビゲーション学習手法を提案した。
著者: Jake Bruce, Niko Suenderhauf, Piotr Mirowski, Raia Hadsell, Michael Milford
分類: cs.AI, cs.LG, cs.RO
原文アブストラクト
Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is that interaction with the real world is costly, but training on limited experience is prone to overfitting. We present a method for learning to navigate, to a fixed goal and in a known environment, on a mobile robot. The robot leverages an interactive world model built from a single traversal of the environment, a pre-trained visual feature encoder, and stochastic environmental augmentation, to demonstrate successful zero-shot transfer under real-world environmental variations without fine-tuning.
