RETALIATE: Learning Winning Policies in First-Person Shooter Games

نویسندگان

  • Megan Smith
  • Stephen Lee-Urban
  • Hector Muñoz-Avila
چکیده

In this paper we present RETALIATE, an online reinforcement learning algorithm for developing winning policies in team firstperson shooter games. RETALIATE has three crucial characteristics: (1) individual BOT behavior is fixed although not known in advance, therefore individual BOTS work as “plugins”, (2) RETALIATE models the problem of learning team tactics through a simple state formulation, (3) discount rates commonly used in Q-learning are not used. As a result of these characteristics, the application of the Q-learning algorithm results in the rapid exploration towards a winning policy against an opponent team. In our empirical evaluation we demonstrate that RETALIATE adapts well when the environment changes.

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

Learning to be a Bot: Reinforcement Learning in Shooter Games

This paper demonstrates the applicability of reinforcement learning for first person shooter bot artificial intelligence. Reinforcement learning is a machine learning technique where an agent learns a problem through interaction with the environment. The Sarsa( ) algorithm will be applied to a first person shooter bot controller to learn the tasks of (1) navigation and item collection, and (2) ...

متن کامل

Game Designers Training First Person Shooter Bots

Interactive training is well suited to computer games as it allows game designers to interact with otherwise autonomous learning algorithms. This paper investigates the outcome of a group of five commercial first person shooter game designers using a custom built interactive training tool to train first person shooter bots. The designers are asked to train a bot using the tool, and then comment...

متن کامل

Apprentissage par renforcement factorisé pour le comportement de personnages non joueurs

In this paper, we apply a general reinforcement learning method to automatically design the behavior of non player characters of the Counter-Strike first person shooter computer game. The result of the learning process is a set of decision trees that represents compactly and easily readable a model of the problem itself and the decision policy of characters. Beyond this example, we discuss the ...

متن کامل

Evolutionary Neural Networks applied in First Person Shooters

Computers games are becoming more and more complex. This calls for better artificial behaviors of the computer opponents. Right now creating these solutions is all done by hand, making it a very labor intensive task. Especially if the number of inputs increases this becomes very impractical. Several learning techniques are created in the scientific world that could be used to make this an autom...

متن کامل

An Empirical Study of Machine Learning Algorithms Applied to Modeling Player Behavior in a “First Person Shooter” Video Game

Modern video games present many challenging applications for artificial intelligence. Agents must not only appear intelligent but must also be fun to play against. In the video game genre of the first person shooter an agent must mimic all the behaviors of a human soldier in a combat situation. The standard opponent in a “first person shooter” uses a finite-state machine and a series of hand co...

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:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007