Search Results for "ai code agent" - Page 2

Java Behaviour Trees is a Java framework for easily building and running generic behaviour trees. Here, "behaviour tree" refers to the technique used to control the behaviour of characters in video games. IMPORTANT NOTE: our source code has been moved to GitHub. You will find it at: https://github.com/gaia-ucm/jbt Note however that all the binary files will still be distributed here at SourceForge.

Ellipsis is a modular, agent-oriented, and extendable toolkit to execute stationary and mobile software agents written in the Java programming language. Ellipsis uses the standard application server JBoss (version 4.2.3 GA) without any modifications. In contrast to existing mobile agent toolkits, Ellipsis has an agent- and message-oriented architecture. Ellipsis is built on top of the JMX architecture. Core Ellipsis components are implemented as MBeans which provides for basic ser-vices...

This project contains the files required to run the Cross-Entropy Relational Reinforcement Learning Agent (CERRLA) algorithm. Note that a copy of the JESS rules engine will also be required.

CARTAGO-WS is a platform for developing SOA applications based on Web Services exploiting agent programming models and technologies.

Software agents and human actors combine their decision making skills to arrive at efficient solutions to real-life planning and scheduling problems, especially in domains where unexpected incidents require changes to existing plans.

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).

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.

MARS (Multi Agent Roundbased Simulator) is a simulator for Multi Agent systems written in java. It sets up on the eclipse platform and is realized as a set of plugins. It was started as a project-group at University of Paderborn in 2010. At the moment there is a second project-group using MARS. The german documentation of first group can be found at http://www.cs.uni-paderborn.de/fileadmin/Informatik/AG-Kleine-Buening/files/ws11/pg-agents-2/Abschlussdoku-pg-1.pdf If you want...

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.

ACLAnalyser is a powerful tool to validate, verify and debug a MAS (Multi Agent Systems). ACLAnalyser sniff all messages exchanged between agents in a MAS, store them in a data base, and recover them later to get interesting information.

Modular version of FAtiMA Agent Architecture. FAtiMA is an Autonomous Agent Architecture with reactive and BDI based deliberative behaviour and with emotions and reasoning capabilities.

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.

nu-BDI is an extension of the Jason agent interpreter aimed at processing norms using constraints on the agent's instantiated plans. The core agent reasoning cycle now includes a component for processing norms and enforcing norm constraints.

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.

breve is a free, open-source 3D multi-agent simulation package designed for simulating decentralized systems and artificial life.

Java framework for agent based application development

Java JNI API for morphological analysis of Russian. Note: C++ JNI code and the core code is at the project http://sourceforge.net/projects/seman/ .

Master's Thesis subject: "Knowledge repositories for effective and secure services executing in agent environment." Goal: Developing optimal method for storing knowledge in distributed agent applications. Java code + LaTeX documents.

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.

SimIS presents an agent-based simulation environment from multiagent research to simulate Internet-of-Services systems. The simulation environment bases on Repast Simphony 1.2 (http://repast.sourceforge.net/).

GridIQ is a testbed for smart grid agents. It enables the JADE agent development platform to integrate with the PSAT power simulation tool.

Simple multi-agent simulation of Darwin's natural selection process

Comprehensive agent-based e-commerce system realizing price negotations and combining: (a) adaptability and intelligence (change strategy according to history of purchases), (b) mobility (based on transfer of negotation modules and agents).