Attentive Relation Network for Object based Video Games
Attentive Relation Network for Object based Video Games
复制标题
基于对象的视频游戏的注意力关系网络
DOI：
10.1109/ijcnn52387.2021.9533369
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Hu Jinglu
中科院分区：
文献类型：
--
作者：
Deng Hangyu;Luo Jia;Hu Jinglu
深度强化学习算法在电子游戏领域取得了巨大进展。然而，该方法仍然存在一些问题，如样本效率低下和泛化能力差。在本文中，我们强调这些问题的部分原因是卷积神经网络（cnn）无法对图像观测中物体之间的潜在关系进行推理。基于这一点，我们试图以一种更有效和可解释的方式来缓解这些问题，包括学习对象的表示和用关系网络（RN）推理它们之间的关系。特征图中的每个像素都被视为一个对象，我们的模型明确地学习对象对之间的关系。这些关系通过注意机制进行总结，然后输入到下游的全连接层中。在实验中，我们的模型与三个典型的基于对象的雅达利游戏的基线模型进行了比较。在相同的超参数设置下，我们的模型仍然具有更好的样本效率和泛化能力。进一步的研究揭示了超参数的影响，并验证了模型的可解释性。
Deep reinforcement learning algorithms have made great progress in video games. However, there are still some problems, such as sample inefficiency and poor generalization. In this paper, we highlight that these problems are partially caused by the inability of convolutional neural networks (CNNs) to reason with the underlying relations between the objects in the image observations. Based on this point, we try to alleviate these problems in a more efficient and explainable way, including learning the representations of objects and reasoning the relations between them with a relation network (RN). Each pixel in the feature maps is treated as an object and our model explicitly learns the relations between object pairs. The relations are summarized through an attention mechanism and then fed into the downstream fully-connected layers. In the experiments, our model is compared with baseline models in three typical object based Atari games. Under the same hyperparameter settings, our model still achieves better sample efficiency and generalization capability. Further studies throw light on the impact of hyperparameters and verify the interpretability of the model.