合成可能な行動条件付き予測器：ロボットナビゲーションのための柔軟なオフポリシー学習
Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation
オフポリシーデータからイベント手がかりを学習し、テスト時にそれらを組み合わせて多様なタスクを達成するフレームワークを提案。シミュレーションと実機のRCカーで自律的にデータ収集・学習し、様々なタスクを実行できることを示した。
著者: Gregory Kahn, Adam Villaflor, Pieter Abbeel, Sergey Levine
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
A general-purpose intelligent robot must be able to learn autonomously and be able to accomplish multiple tasks in order to be deployed in the real world. However, standard reinforcement learning approaches learn separate task-specific policies and assume the reward function for each task is known a priori. We propose a framework that learns event cues from off-policy data, and can flexibly combine these event cues at test time to accomplish different tasks. These event cue labels are not assumed to be known a priori, but are instead labeled using learned models, such as computer vision detectors, and then `backed up' in time using an action-conditioned predictive model. We show that a simulated robotic car and a real-world RC car can gather data and train fully autonomously without any human-provided labels beyond those needed to train the detectors, and then at test-time be able to accomplish a variety of different tasks. Videos of the experiments and code can be found at https://github.com/gkahn13/CAPs
