Reinforcement Learning In Real-Time Strategy Games

نویسندگان

  • António Gusmão
  • Tapani Raiko
چکیده

We consider the problem of effective and automated decisionmaking in modern real-time strategy (RTS) games through the use of reinforcement learning techniques. RTS games constitute environments with large, high-dimensional and continuous state and action spaces with temporally-extended actions. To operate under such environments we propose Exlos, a stable, model-based MonteCarlo method. Contrary to existing model-based algorithms, Exlos assumes models are imperfect, reducing their influence in the decision-making process. Its effectiveness is further improved by including a novel online search procedure in the control policy. Experimental results in a testing environment show the superiority of Exlos in discrete state spaces when compared to traditional reinforcement learning methods such as Q-learning and Sarsa. Furthermore, Exlos is shown to be effective and efficient on an environment with a large continuous state and action space. This work is a summary of [Gusmao 2011].

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

Robust Opponent Modeling in Real-Time Strategy Games using Bayesian Networks

Opponent modeling is a key challenge in Real-Time Strategy (RTS) games as the environment is adversarial in these games, and the player cannot predict the future actions of her opponent. Additionally, the environment is partially observable due to the fog of war. In this paper, we propose an opponent model which is robust to the observation noise existing due to the fog of war. In order to cope...

متن کامل

Hierarchical Reinforcement Learning on the Virtual Battlefield

This paper investigates the potential of flat and hierarchical reinforcement learning (HRL) for solving problems within strategy games. A HRL method, Max-Q, is applied to a unit transportation task modelled within a simplified, discrete real-time strategy game engine, and its performance compared to that of flat Q-learning. It is shown that reinforcement learning approaches, and especially hier...

متن کامل

Modeling Unit Classes as Agents in Real-Time Strategy Games

We present CLASSQL, a multi-agent model for playing real-time strategy games, where learning and control of our own team’s units is decentralized; each agent uses its own reinforcement learning process to learn and control units of the same class. Coordination between these agents occurs as a result of a common reward function shared by all agents and synergistic relations in a carefully crafte...

متن کامل

Hierarchical Reinforcement Learning for Real-Time Strategy Games

Real-Time Strategy (RTS) games can be abstracted to resource allocation applicable in many fields and industries. We consider a simplified custom RTS game focused on mid-level combat using reinforcement learning (RL) algorithms. There are a number of contributions to game playing with RL in this paper. First, we combine hierarchical RL with a multi-layer perceptron (MLP) that receives higher-or...

متن کامل

Reinforcement Learning approach for Real Time Strategy Games Battle city and S3

In this paper we proposed reinforcement learning algorithms with the generalized reward function. In our proposed method we use Q-learning and SARSA algorithms with generalised reward function to train the reinforcement learning agent. We evaluated the performance of our proposed algorithms on two real-time strategy games called BattleCity and S3. There are two main advantages of having such an...

متن کامل

CLASSQ-L: A Q-Learning Algorithm for Adversarial Real-Time Strategy Games

We present CLASSQ-L (for: class Q-learning) an application of the Q-learning reinforcement learning algorithm to play complete Wargus games. Wargus is a real-time strategy game where players control armies consisting of units of different classes (e.g., archers, knights). CLASSQ-L uses a single table for each class of unit so that each unit is controlled and updates its class’ Qtable. This enab...

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 2012