位置・速度エンコーダによる構造化状態表現の教師なし学習
PVEs: Position-Velocity Encoders for Unsupervised Learning of Structured State Representations
画像からタスク関連物体の位置と速度を教師なしで符号化するPVEを提案し、物理世界の事前知識に基づく整合性で学習、複数のシミュレーション制御タスクで有効性を予備的に示した。
著者: Rico Jonschkowski, Roland Hafner, Jonathan Scholz, Martin Riedmiller
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
We propose position-velocity encoders (PVEs) which learn---without supervision---to encode images to positions and velocities of task-relevant objects. PVEs encode a single image into a low-dimensional position state and compute the velocity state from finite differences in position. In contrast to autoencoders, position-velocity encoders are not trained by image reconstruction, but by making the position-velocity representation consistent with priors about interacting with the physical world. We applied PVEs to several simulated control tasks from pixels and achieved promising preliminary results.
