ViSaRL: 人間の顕著性に導かれた視覚強化学習
ViSaRL: Visual Reinforcement Learning Guided by Human Saliency
人間の視覚的注意(顕著性)を強化学習に組み込み、高次元画像入力からの効率的な視覚表現学習を実現し、サンプル効率・成功率・汎化性能を向上させた。
著者: Anthony Liang, Jesse Thomason, Erdem Bıyık
分類: cs.RO, cs.LG
原文アブストラクト
Training robots to perform complex control tasks from high-dimensional pixel input using reinforcement learning (RL) is sample-inefficient, because image observations are comprised primarily of task-irrelevant information. By contrast, humans are able to visually attend to task-relevant objects and areas. Based on this insight, we introduce Visual Saliency-Guided Reinforcement Learning (ViSaRL). Using ViSaRL to learn visual representations significantly improves the success rate, sample efficiency, and generalization of an RL agent on diverse tasks including DeepMind Control benchmark, robot manipulation in simulation and on a real robot. We present approaches for incorporating saliency into both CNN and Transformer-based encoders. We show that visual representations learned using ViSaRL are robust to various sources of visual perturbations including perceptual noise and scene variations. ViSaRL nearly doubles success rate on the real-robot tasks compared to the baseline which does not use saliency.
