arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.06392cs.LGstat.ML
收藏

第一人称射击游戏中任务相关目标的发现与分类

Task-Relevant Object Discovery and Categorization for Playing First-person Shooter Games

Rutgers University(罗格斯大学)

Junchi Liang, Abdeslam Boularias

摘要:

我们考虑学习玩第一人称射击(FPS)视频游戏的问题,使用原始屏幕图像作为观察和键盘输入作为动作。在这种类型的应用中,观测的高维性导致对无模型方法(例如深度Q网络(DQN)及其递归变体DRQN)的训练数据的禁止性需求。因此,最近的工作集中在学习低维表示,可以减少对数据的需求。本文提出了一种新的和有效的方法来学习这样的表示。从连续帧的光流中检测其显著段,并基于其特征描述符进行聚类。集群通常对应于不同的发现的对象类别。在新帧中检测到的片段然后基于它们最近的聚类进行分类。由于只有少数类别与给定任务相关,因此类别的重要性被定义为其出现与智能体性能之间的相关性。结果被编码为指示帧中的对象及其位置的矢量,并用作DRQN的侧输入。在游戏Doom上的实验为这种方法的优点提供了很好的证据。

英文摘要:

We consider the problem of learning to play first-person shooter (FPS) video games using raw screen images as observations and keyboard inputs as actions. The high-dimensionality of the observations in this type of applications leads to prohibitive needs of training data for model-free methods, such as the deep Q-network (DQN), and its recurrent variant DRQN. Thus, recent works focused on learning low-dimensional representations that may reduce the need for data. This paper presents a new and efficient method for learning such representations. Salient segments of consecutive frames are detected from their optical flow, and clustered based on their feature descriptors. The clusters typically correspond to different discovered categories of objects. Segments detected in new frames are then classified based on their nearest clusters. Because only a few categories are relevant to a given task, the importance of a category is defined as the correlation between its occurrence and the agent's performance. The result is encoded as a vector indicating objects that are in the frame and their locations, and used as a side input to DRQN. Experiments on the game Doom provide a good evidence for the benefit of this approach.

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。

↑