CLOUD: 教師なしダイナミクスの対照学習
CLOUD: Contrastive Learning of Unsupervised Dynamics
ランダム探索データから、対照推定を用いて順・逆ダイナミクスを完全教師なしで学習する手法を提案し、目標指向計画や観察からの模倣で有効性を示した。
著者: Jianren Wang, Yujie Lu, Hang Zhao
分類: cs.RO, cs.CV
原文アブストラクト
Developing agents that can perform complex control tasks from high dimensional observations such as pixels is challenging due to difficulties in learning dynamics efficiently. In this work, we propose to learn forward and inverse dynamics in a fully unsupervised manner via contrastive estimation. Specifically, we train a forward dynamics model and an inverse dynamics model in the feature space of states and actions with data collected from random exploration. Unlike most existing deterministic models, our energy-based model takes into account the stochastic nature of agent-environment interactions. We demonstrate the efficacy of our approach across a variety of tasks including goal-directed planning and imitation from observations. Project videos and code are at https://jianrenw.github.io/cloud/.
