深層後継表現を用いた視覚的意味計画
Visual Semantic Planning using Deep Successor Representations
視覚環境で初期状態から目標状態へ遷移する行動列を予測するため、模倣学習で強化学習をブートストラップし、後継表現に基づく深層予測モデルでタスク間の汎化を実現した。
著者: Yuke Zhu, Daniel Gordon, Eric Kolve, Dieter Fox, Li Fei-Fei, Abhinav Gupta, Roozbeh Mottaghi, Ali Farhadi
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
A crucial capability of real-world intelligent agents is their ability to plan a sequence of actions to achieve their goals in the visual world. In this work, we address the problem of visual semantic planning: the task of predicting a sequence of actions from visual observations that transform a dynamic environment from an initial state to a goal state. Doing so entails knowledge about objects and their affordances, as well as actions and their preconditions and effects. We propose learning these through interacting with a visual and dynamic environment. Our proposed solution involves bootstrapping reinforcement learning with imitation learning. To ensure cross task generalization, we develop a deep predictive model based on successor representations. Our experimental results show near optimal results across a wide range of tasks in the challenging THOR environment.
