Search Results for "agents"

EcoLab is a C++ based Agent Based Modelling system, with emphasis on high performance computing for scaling to large simulations.

It is an open source scientific library that is focused on multi-agent simulations on graphs. It prepares basic toolkit for agents, models, timers, graphs, nodes and edges. It is also accompanied with tools for data processing.

Roboschool is a set of open source robot simulation environments for reinforcement learning, created as an alternative to the Mujoco physics engine. It integrates with OpenAI Gym and provides a variety of continuous control tasks, including humanoid locomotion, quadrupeds, and robotic arms. The library is built on the Bullet Physics engine, making it accessible without the licensing requirements of Mujoco. Roboschool includes training scripts and examples for applying reinforcement learning...

The Mobility Open Architecture Simulation and Tools (MOAST) framework aids in the development of autonomous robots. It includes an architecture, control modules, interface specs, and data sets and is fully integrated with the USARSim simulation system.

Simultra is an open-source, hybrid road traffic simulator designed to handle large roadmaps in real-time. It combines microscopic and mesoscopic simulations into one multiagent hybrid simulator. The large-scale maps are modelled mesoscopically in real-time, and the complex traffic interactions benefit from detailed agent-based microscopic simulations. To resolve the concurrency issues within the maps representation and the meso-micro transitions, Simultra combines an event-based mesoscopic...

Spark is a physical simulation system. The primary purpose of this system is to provide a *generic* simulator for different kinds of simulations. In these simulations, agents can participate as external processes.

...Its main intention is to provide a sustainable and consistent framework for the implementation and application of model concepts, constitutive relations, discretizations, and solvers. It has been successfully applied to CO2 storage scenarios, environmental remediation problems, transport of therapeutic agents through biological tissue, and subsurface-atmosphere coupling. DuMuX is part of the OPM (Open Porous Media) initiative, opm-project.org.

Spirit Development Kit is a SDK for development, simulation, and evolving of intelligent agents. Includes a library of AI algorithms and more a framework for modelling and simulations.

Laputa is a research tool and a sandbox environment for simulating the attainment of knowledge in social networks, such as scientific departments, editorial boards, expert groups, and the general public. It was developed at the philosophy department at the university of Lund.

EVO is a simulation platform for co-evolving the morphology and the behavior of 3D artificial agents in a complex environment. This project directly follows the original work of Karl Sims. It puts together complex creatures, a GA & Open Dynamics Engine.

BitBang is an agent-based simulation framework, best suited for complex systems or artificial life research. It is developed with ease of integration in mind, allowing the interplay with existing 3D and physics engines.

Critterding is a "Petri dish" universe in 3D that demonstrates evolving artificial life. Critters start out with completely random brains and bodies, but will automatically start evolving into something with much better survival skills.

This project has been moved to https://bitbucket.org/pbazant/evoversum/src/master/ . Evoversum is a fast Darwinian evolution simulator. The program simulates a 2D world populated with "animals" which struggle for food, reproduce and may also eat each other. The subject of evolution is their behavior, which may become quite complex. There is an updated video tutorial at http://www.youtube.com/watch?v=nPkZvyVDWJU !

The Mars Rover Simulator project is based on the evolutionary robotics paradigm where an artificial agent acquires its skills through the process of artificial evolution. This simulator can be useful to evolve neural network controllers for the rover

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

BehaveRT is a C++ library that helps to create interactive simulations of a large number of virtual agents. Hardware acceleration (GPUs) guarantees high performances.

Ouroborus is an artificial life framework for mobile agents on a background of cellular automata. It can be used to teach and research topics such as population genetics, ecology and evolution. The demo includes a curses view and live Csound audio.

UniNetS is an extensible C++ API for simulating any kind of network consisting of inter-connected/communicating agents.

Elysia is an attempt to study the complex process behind decision making in neural systems. An evolved entity approach is used to converge on an 'intelligence' solution through genetic algorithms as well as adaptable models of distributed 'thinking'.

This project has been renamed to oooark. Old file releases will still be available here. uvsim is a project focused on enabling algorithm development for unmanned systems. It is being constructed to provide an identical interface to simulations and h

LabLOVE (Life On a Virtual Environment) is an evolutionary multi-agent simulation environment. It is fast, modular and extensible. Contains the reference implementation for the gridbrain algorithm.

Animants are virtual ants. Their name comes from the combination of "ants" and "animats", an animat being "a sofware approximation of a living creature". Animants aim to simulate the behaviour of living animals.

RegMAS (Regional Multi Agent Simulator) is a spatially explicit multi-agent model framework, developed in C++ language and designed for long-term simulations of effects of government policies over agricultural systems (farm sizes, incomes, land use..).

A suite of machine learning benchmarks where each agent must solve a lot of different tasks without recompilation. This means that the programmers cannot manually specify topologies or adjust parameters to specific tasks.

ARTIcomm (ARTIFICIAL communities) – project for developing communities of intelligent embodied agents with artificial neural networks using evolutionary algorithms.