Automatically Reinforcing a Game AI

نویسندگان

  • David Lupien St-Pierre
  • Jean-Baptiste Hoock
  • Jialin Liu
  • Fabien Teytaud
  • Olivier Teytaud
چکیده

A recent research trend in Artificial Intelligence (AI) is the combination of several programs into one single, stronger, program; this is termed portfolio methods. We here investigate the application of such methods to Game Playing Programs (GPPs). In addition, we consider the case in which only one GPP is available by decomposing this single GPP into several ones through the use of parameters or even simply random seeds. These portfolio methods are trained in a learning phase. We propose two different offline approaches. The simplest one, BestArm, is a straightforward optimization of seeds or parameters; it performs quite well against the original GPP, but performs poorly against an opponent which repeats games and learns. The second one, namely Nash-portfolio, performs similarly in a “one game” test, and is much more robust against an opponent who learns. We also propose an online learning portfolio, which tests several of the GPP repeatedly and progressively switches to the best one using a bandit algorithm.

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

Automatically Generating Game Tactics through Evolutionary Learning

trolled opponents in video games is called game AI. Adaptive game AI can improve the entertainment value of games by allowing computer-controlled opponents to fix weaknesses automatically in the game AI and to respond to changes in human-player tactics. Dynamic scripting is a reinforcement learning approach to adaptive game AI that learns, during gameplay, which game tactics an opponent should ...

متن کامل

Automatically Acquiring Domain Knowledge For Adaptive Game AI Using Evolutionary Learning

Game AI is the decision-making process of computer-controlled opponents in computer games. Adaptive game AI can improve the entertainment value of computer games. It allows computercontrolled opponents to automatically fix weaknesses in the game AI and respond to changes in human-player tactics. Dynamic scripting is a recently developed approach for adaptive game AI that learns which tactics (i...

متن کامل

Automatically Generating Game Tactics via Evolutionary Learning

The decision-making process of computer-controlled opponents in video games is called game AI. Adaptive game AI can improve the entertainment value of games by allowing computer-controlled opponents to fix weaknesses automatically in the game AI, and to respond to changes in human-player tactics. Dynamic scripting is a reinforcement learning approach to adaptive game AI that learns, during game...

متن کامل

Opponent modelling for case-based adaptive game AI

In previous work we introduced a novel approach to adaptive game AI that was focussed on the rapid and reliable adaptation to game circumstances. We named the approach ‘case-based adaptive game AI’. In the approach, domain knowledge required to adapt to game circumstances is gathered automatically by the game AI, and is exploited immediately (i.e., without trials and without resource-intensive ...

متن کامل

Rapidly Adapting Game AI

Current approaches to adaptive game AI require either a high quality of utilised domain knowledge, or a large number of adaptation trials. These requirements hamper the goal of rapidly adapting game AI to changing circumstances. In an alternative, novel approach, domain knowledge is gathered automatically by the game AI, and is immediately (i.e., without trials and without resource-intensive le...

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:
  • CoRR

دوره abs/1607.08100  شماره 

صفحات  -

تاریخ انتشار 2016