English中文
将人工智能用起来
2019年6月18-21日
北京,中国

基于Spark使用AI来玩游戏(Game playing using AI on Spark)

此演讲使用中文 (This will be presented in Chinese)

Shan Yu (Intel)
16:2017:00 Thursday, June 20, 2019
实施人工智能 (Implementing AI)
Location: 多功能厅8A+B(Function Room 8A+B)
Average rating: ****.
(4.00, 1 rating)

必要预备知识 (Prerequisite Knowledge)

  • General knowledge of Spark and deep neural networks
  • Familiarity with reinforcement learning (useful but not required)

您将学到什么 (What you'll learn)

  • Discover the pros and cons of using Spark for implementing game-related AI

描述 (Description)

Using AI to play games is often perceived as an early step toward achieving general machine intelligence, as the ability to reason and make decisions based on sensed information is an essential part of general intelligence. Games are good playgrounds for experimenting with intelligent agents as the goals, actions, and rules are often well-defined and abstract. People have been interested in using AI to play games for quite a while. The recent development of deep neural networks allowed visual information in games to be processed effectively and directly used for the decision making of agents, and the area of deep reinforcement learning and metalearning are also being explored in this aspect.

Shan Yu offers an overview of and shares lessons learned from her attempts using AI on Spark to play games: for example, whether Spark is a good fit for implementing game-related AI, which parts need to be improved, and the changes Spark has made in the area of AI game playing.

使用AI来玩游戏通常被认为是实现通用机器智能的初始一步,因为基于感知到的信息进行推理和决策的能力是通用智能的重要组成部分。而游戏则是试验智能代理机器人的好场合,因为它们的目标和行动规则通常是被明确定义和抽象好的。人们一直对使用AI玩游戏非常感兴趣。深度神经网络的最新进展允许有效地处理游戏中的视觉信息并直接用于代理机器人做决策。同时深度强化学习和元学习也正在被用于探索这个领域。

在本次议题中我们将分享基于Spark使用AI玩游戏的经验。演讲会包括演示和实验的一些细节,以及我们学到的经验,例如,Spark是否适合实现与游戏相关的AI?为此,它的哪些部分需要改进?以及Spark在AI游戏领域的变化。

Photo of Shan Yu

Shan Yu

Intel

Shan Yu is a machine learning software engineer at Intel.

Intel机器学习软件工程师。

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)