TerraSim - a simulated environment

  •        37

TerraSim is a flexible simulation server. Designed for usage in AI research, it is specifically built to allow agents to learn and reason about the world's intrinsic workings. TerraSim also allows for simple creation of new, user defined worlds.

http://terrasim.codeplex.com/

Tags
Implementation
License
Platform

   




Related Projects

Crowd Simulation Framework


CSF-Crowd Simulation Framework A Massive Crowd Simulation is a computer simulation of a crowd of agents. Agents are digital characters with a certain artificial intelligence. The individual agents can act on their own, they don't need to be pre-prog

HTML5-boid-simulation - Simulation of boids/agents in an artificial world.


Simulation of boids/agents in an artificial world.

dengueSim - Dengue Environment Simulation in .NET using Multi-Agents System


Dengue Environment Simulation in .NET using Multi-Agents System

ap_scouts - SImulation of a swarm of agents using Artificial Physics (AP) for maintaing formation.


SImulation of a swarm of agents using Artificial Physics (AP) for maintaing formation.

RescueStarterPack - Project of Sample agents and Ri-one viewer for RoboCup Rescue Simulation


Project of Sample agents and Ri-one viewer for RoboCup Rescue Simulation



open SPEAR


open SPEAR stands for open Simulator of Physical Environment for Agents Research. It is a C++ library designed to build efficient simulation of multi-agents and robotics simulation. The main audience for this project is the robotician/artificial life com

jimmikaelkael-simbad


Simbad is a Java 3d robot simulator for scientific and educationnal purposes. It is mainly dedicated to researchers/programmers who want a simple basis for studying Situated Artificial Intelligence, Machine Learning, and more generally AI algorithms, in the context of Autonomous Robotics and Autonomous Agents. It is not intented to provide a real world simulation and is kept voluntarily readable and simple. Simbad enables programmers to write their own robot controller, modify the environment an

Agents


Agents (A Game theoretic Evolutionary Network Traffic Simulation) is a toolkit for the analysis of selfish agents in networks by means of evolutionary game theory. Simulations of replicator and other dynamics can be plotted, visualised and analysed.

IA1 - Agents and Decision Tree Learning


Agents and Decision Tree Learning

agency - An extract from Tegu's WorkloadManager, interchangeable machine learning agents.


An extract from Tegu's WorkloadManager, interchangeable machine learning agents.

AgEx


AgEx is a financial market simulation tool for software agents. This tool allows traders launched from distinct computers to act in the same market. It makes easier the design, implementation and test of trader agents and new trading techniques.

gardaud-Kitsune


Kitsune is a simulation tool written in Java with Swing that allows to design the layout of a building, position agents and define their behaviors, and run a simulation of a fire evacuation. Written as part of a Computer Science senior thesis at Oxford Brookes.

snooker-angles - Simple simulation of a single snooker ball for learning about bearings.


Simple simulation of a single snooker ball for learning about bearings.

cge-fluidsim - A dynamic fluid simulation for mobile devices experiment/learning experience


A dynamic fluid simulation for mobile devices experiment/learning experience

Circuit - boolean circuit simulation - testbed for learning about Scala, not meant to be useful


boolean circuit simulation - testbed for learning about Scala, not meant to be useful

PLASTK


A Python class library of tools for learning agents, including reinforcement learning algorithms, function approximators, and vector quantizations algorithms. (Pronounced quot;plasticquot;.)

IAL-MaxEntropy


Intelligent Agents Lab - Maximum Entropy Inverse Reinforcement Learning implementation for learning opponent motion model

taylortom-Cogito


Final year university project looking into using machine learning techniques in a game environment. The game takes Lemming's as inspiration, with the agents able to learn optimum paths through the 2D environment using reinforcement learning.

lstms_for_predictive_maintenance - LSTMS for Predictive Maintenance


Deep learning has proven to show superior performance in certain domains such as object recognition and image classification. It has also gained popularity in domains such as finance where time-series data plays an important role. Predictive Maintenance is also a domain where data is collected over time to monitor the state of an asset with the goal of finding patterns to predict failures which can also benefit from certain deep learning algorithms. Among the deep learning methods, Long Short Term Memory LSTM networks are especially appealing to the predictive maintenance domain due to the fact that they are very good at learning from sequences. This fact lends itself to their applications using time series data by making it possible to look back for longer periods of time to detect failure patterns. In this notebook, we build an LSTM network for the data set and scenario described at Predictive Maintenance Template to predict remaining useful life of aircraft engines using the Turbofan Engine Degradation Simulation Data Set. In summary, the template uses simulated aircraft sensor values to predict when an aircraft engine will fail in the future so that maintenance can be planned in advance.We suggest that you use Data Science Virtual Machine for this tutorial which comes with CNTK pre-installed. You can then configure to enable CNTK as Keras back end.

Evolve


Evolve is a simulation written in java that uses the Genetic Algorithm to evolve intelligent agents acting in a rich environment.