arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.09448cs.AIcs.CV
收藏

稀疏奖励视觉场景中基于动量记忆内在奖励的图像增强

Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes

Xi’an Jiaotong University(西安交通大学)

Zheng Fang, Biao Zhao, Guizhong Liu

摘要:

现实生活中的许多场景都可以抽象为稀疏奖励视觉场景,在这种场景中,智能体很难在只接受图像和稀疏奖励的情况下处理任务。我们建议将这个问题分解为两个子问题:视觉表示和稀疏奖励。为了解决这些问题,一个新的框架IAMMIR相结合的自我监督表示学习与内在动机。对于视觉表示,获得由图像增强的前向动力学和奖励的组合驱动的表示。对于稀疏奖励,设计了一种新的内在奖励,即动量记忆内在奖励(MMIR)。它利用当前模型(在线网络)和历史模型(目标网络)的输出的差异来表示Agent的状态熟悉度。我们的方法进行评估的视觉导航任务稀疏奖励Vizdoom。实验表明,该方法在样本效率方面达到了最先进的水平,比现有的方法至少快2倍,达到100%的成功率。

英文摘要:

Many scenes in real life can be abstracted to the sparse reward visual scenes, where it is difficult for an agent to tackle the task under the condition of only accepting images and sparse rewards. We propose to decompose this problem into two sub-problems: the visual representation and the sparse reward. To address them, a novel framework IAMMIR combining the self-supervised representation learning with the intrinsic motivation is presented. For visual representation, a representation driven by a combination of the imageaugmented forward dynamics and the reward is acquired. For sparse rewards, a new type of intrinsic reward is designed, the Momentum Memory Intrinsic Reward (MMIR). It utilizes the difference of the outputs from the current model (online network) and the historical model (target network) to present the agent's state familiarity. Our method is evaluated on the visual navigation task with sparse rewards in Vizdoom. Experiments demonstrate that our method achieves the state of the art performance in sample efficiency, at least 2 times faster than the existing methods reaching 100% success rate.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑