Evolving Mario to Maximize Coin Score Using Neat and Novelty

نویسندگان

  • Amy Han
  • Jeremy Han
چکیده

Genetic algorithms can be used to evolve agents that will complete game tasks in a given game environment. In this paper, we discuss our experimental results using NEAT and Novelty to evolve Mario, from the popular game Super Mario Bros, to maximize his coin score. To conduct our experiments, we developed our own Mario simulator, creating a small world and a big world. Each world has an easy and hard version; the addition of coin boxes is what defines a world to be difficult. Just like in the original SMB, we added hidden rooms that contain many coins. However, finding the hidden room is the most difficult part. We hypothesized that Novelty would outperform NEAT because of its exploratory nature, while NEAT would focus more on getting the coins that are easy to obtain. Our results indicated that without an input that tells Mario what type of coin is nearest to him, Novelty significantly outperforms NEAT. However, with the input, NEAT can perform on par, or even better than Novelty at times. We argue that the reason for his discrepancy is that the addition of the input makes the task less deceptive for NEAT, which closes the performance gap between NEAT and Novelty.

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

Evolving a Dynamic Predictive Coding Mechanism for Novelty Detection

Novelty detection is a machine learning technique which identifies new or unknown information in data sets. We present our current work on the construction of a new novelty detector based on a dynamical version of predictive coding. We compare three evolutionary algorithms, a simple genetic algorithm, NEAT and FS-NEAT, for the task of optimising the structure of an illustrative dynamic predicti...

متن کامل

Creating a Traffic Merging Behavior Using NeuroEvolution of Augmenting Topologies

One of the main goals in developing an autonomous vehicle is programming the action of merging into the traffic lane from an entrance ramp. We seek to create such a behavior through the use of NeuroEvolution of Augmenting Topologies (NEAT) by evolving an agent over many generations to maximize a certain prescribed fitness function, which encourages a smooth merging behavior without crashing. Ou...

متن کامل

The validity of the non-exercise activity thermogenesis questionnaire evaluated by objectively measured daily physical activity by the triaxial accelerometer

BACKGROUND Physical inactivity is a major cardiovascular risk factor. Recently, we showed that non-exercise activity thermogenesis (NEAT) assessed by the self-reported questionnaire is favorably associated with metabolic risks in patients with type 2 diabetes. The purpose of the present study was to examine the validity of the questionnaire by comparing with objectively measured daily physical ...

متن کامل

PMCNS: Using a Progressively Stricter Fitness Criterion to Guide Novelty Search

Novelty search is an evolutionary approach in which the population is driven towards behavioural innovation instead of towards a fixed objective. The use of behavioural novelty to score candidate solutions precludes convergence to local optima. However, in novelty search, significant effort may be spent on exploration of novel, but unfit behaviours. The authors propose progressive minimal crite...

متن کامل

Comparing Adaptivity of Ants using NEAT and rtNEAT

Although individual ants have an extremely basic intelligence, and are completely incapable of surviving on their own, colonies of ants can develop remarkably sophisticated and biologically successful behavior. This paper discusses a set of experiments which attempt to simulate one of these behaviors, namely the ability of ants to place pheromones as a way of communication. These experiments in...

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 2016