The Angry Birds AI Competition

نویسندگان

  • Jochen Renz
  • Xiaoyu Ge
  • Stephen Gould
  • Peng Zhang
چکیده

SUMMER 2015 85 The aim of the Angry Birds AI competition (AIBIRDS) is to build intelligent agents that can play novel Angry Birds levels better than the best human players. The competition was initiated in 2012 by the authors of this report and is held in collocation with some of the major AI conferences such as the International Joint Conference on Artificial Intelligence in 2013 and again in 2015, and the European Conference on Artificial Intelligence conference in 2014. Angry Birds is a popular physics-based puzzle game developed by the company Rovio that requires players to use a slingshot to shoot birds toward green pigs protected by a physical structure (see figure 1). The actions available to players are simple, the release point (x, y) of the bird from the slingshot and the time (t) after release at which the special power of the bird is activated. A level is solved once all pigs are destroyed; most levels can be solved using up to five birds. Different birds have different behaviors and special powers, and while the player knows the order in which birds will appear on the slingshot, the player cannot manipulate this order. While this intuitively sounds very simple, it is a very hard problem for AI as the action space is continuous and the exact outcome of each action is unknown without simulating it. The built-in physics simulator can deterministically

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

AIBIRDS: The Angry Birds Artificial Intelligence Competition

The Angry Birds AI Competition (aibirds.org) has been held in conjunction with the AI 2012, IJCAI 2013 and ECAI 2014 conferences and will be held again at the IJCAI 2015 conference. The declared goal of the competition is to build an AI agent that can play Angry Birds as good or better than the best human players. In this paper we describe why this is a very difficult problem, why it is a chall...

متن کامل

AKBABA: The KBSG 2013 Team for the Angry Birds AI Competition

This paper describes Akbaba, the KBSG’s agent entry for the 2013 Angry Birds AI Competition (ABAIC) held at IJCAI–13. We describe our research background and present the design of our agent, thereby briefly showing how we differ from the sample agent delivered with the ABAIC framework.

متن کامل

Angry Birds as a Challenge for Artificial Intelligence

The Angry Birds AI Competition has been held annually since 2012 in conjunction with some of the major AI conferences, most recently with IJCAI 2015. The goal of the competition is to build AI agents that can play new Angry Birds levels as good as or better than the best human players. Successful agents should be able to quickly analyze new levels and to predict physical consequences of possibl...

متن کامل

Creating a Hyper-Agent for Solving Angry Birds Levels

Over the past few years the Angry Birds AI competition has been held in an attempt to develop intelligent agents that can successfully and efficiently solve levels for the video game Angry Birds. Many different agents and strategies have been developed to solve the complex and challenging physical reasoning problems associated with such a game. However, the performance of these various agents i...

متن کامل

The 2017 AIBIRDS Competition

This paper presents an overview of the sixth AIBIRDS competition, held at the 26th International Joint Conference on Artificial Intelligence. This competition tasked participants with developing an intelligent agent which can play the physics-based puzzle game Angry Birds. This game uses a sophisticated physics engine that requires agents to reason and predict the outcome of actions with only l...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • AI Magazine

دوره 36  شماره 

صفحات  -

تاریخ انتشار 2015