Search Results for "framework" - Page 4

This Java-application contains all required components to simulate a game of Ms. Pac-Man and let an agent learn intelligent playing behaviour using reinforcement learning and either Q-Learning or SARSA. The framework was developed by Luuk Bom and Ruud Henken, under supervision of Marco Wiering, Department of Artificial Intelligence, University of Groningen. It formed the basis of a bachelor's thesis titled "Using reinforcement learning with relative input to train Ms. Pac-Man", L.A.M. Bom (2012).

Search Agents - a framework for collaboration of meta-heuristic agents

...The goal is to provide a uniform interface for describing problems, running evolutionary algorithms, and accumulating results. The Java Evolutionary Computation Library is no longer under active development. We suggest the MOEA Framework (http://www.moeaframework.org/), jMetal (http://jmetal.sourceforge.net/), ECJ (http://cs.gmu.edu/~eclab/projects/ecj/) or JGAP (http://jgap.sourceforge.net/) as alternatives.

Augmented Syntax Diagrams (ASDs) provide a framework to represent grammars of natural languages as directed graphs -- that is, as networks of nodes and edges. Nodes represent instances (or usages) of words and phrase types in a language such as English.

JBoost is a simple, robust system for classification. JBoost contains implementations of several boosting algorithms in an alternating decision tree framework. In addition, JBoost provides extensible software for adding more learning algorithms.

EpochX is an open source genetic programming framework, specifically for analysing the properties of evolutionary automatic programming. It supports 3 popular representations - Strongly-Typed GP, Context-Free Grammar GP and Grammatical Evolution.

R. is a GNU/GPL licensed framework for transporting data residing in RDB into the Semantic Web, which provides a friendly GUI, as well as enough expressivity for creating RDF dumps of RBD data. Video: http://www.youtube.com/watch?v=pk7izhFeuf0

This is a small framework for Q(0) with a feedforward-neural net. The example application is a agent in 2D, which learns to balance a pole.

Wir entwickeln ein Framework für agentenbasierte Spiele. Wir machen das im Rahmen des Kurses "Simulationstechniken" des Fachs AI an der FHTW.

A multi-agent architecture for building interactive dramas. It uses the Jason's BDI engine, being the Jason's agent-oriented programming language utilized for performing the drama management and for authoring behaviors for the characters.

This project implements the "fifteen puzzle", but it has a twist: the program can solve the puzzle perfectly. The project contains a simple JAVA framework that implements heuristic goal-seeking algorithms. We use this to search for the best solution, but the framework is general-purpose and can be used for similar one-person puzzles. Using this framework will allow developers to focus on a specific domain of interest, while leaving many of the AI concepts and goal-searching concepts to be implemented by the framework The front-end classes use Swing and thus can be run via the Web. ...

Nengo is a suite for building and simulating models of large neural networks. It is based on Eliasmith & Anderson's Neural Engineering Framework, which provides a coherent theory of computation, representation, and dynamics in neural circuits.

Justhink is a framework for develop artificial intelligence simulations. The Framework provides a simulation software and an API to develop external modules that are plugged into simulation, such as the problem/mission and artificial intelligence modules

The Swarm Framework was created by the Santa Fe Institute for multi-agent based simulations. The original source code was written in Objective C. This project aims to create a replacement for Swarm bindings for Java which needs native code to work.

Ontology MApping FRAmework Toolkit allows to create semantic relations between two (source and target) ontologies, and apply such relations in translating source ontology instances into target ontology instances.

A versatile and lightweight multi-agent deployment framework

RoboBeans is an interface to the "Robocup 2D Soccer Simulation Server" that allows developers to write Robocup teams\agents concentrating on behaviour and AI without having to worry about syntax of communication or network issues.

A Machine Learning and Data Retrieval Framework

Sleepwalker aims to provide a highly abstract, universal, reusable, extensible Java-based genetic algorithms framework which can be used as a basis for modelling and programming virtually any practical optimisation problem.

X-GAT (XML-based Genetic Algorithm Toolkit) is a Java framework to optimize problems with Genetic Algorithms (GAs). Differently from other frameworks, X-GAT contains ready-to-use GAs implementations and new features can be easily added.

This project provides a java implementation of the Captcha project ( see http://www.captcha.net ). A CAPTCHA is a program that can generate and grade tests that: -Most humans can pass. -Current computer programs can't pass.

Java framework for agent based application development

This project is an integration of the ALIVE framework, based on Organisational theory, into commercial games, providing game AI developers with tools to model gaming scenarios using social structures.

POGG (Programação Orientada a Gráficos de Gantt) é um modelo de programação que permite a distribuição de tarefas num Sistema Multiagente (SMA) criado com a plataforma JADE (Java Agent DEvelopment Framework), formando uma grade computacional.

DCOPolis is a framework for comparing and deploying distributed decision processes in heterogeneous environments, including simulation in a virtual machine.