Search Results for "agents"

PySC2 is DeepMind's Python component of the StarCraft II Learning Environment (SC2LE). It exposes Blizzard Entertainment's StarCraft II Machine Learning API as a Python RL Environment. This is a collaboration between DeepMind and Blizzard to develop StarCraft II into a rich environment for RL research. PySC2 provides an interface for RL agents to interact with StarCraft 2, getting observations and sending actions. The easiest way to get PySC2 is to use pip. That will install the pysc2 package...

Biogenesis is an artificial life program that simulates the processes involved in the evolution of organisms. It shows colored segment based organisms that mutate and evolve in a 2D environment. Biogenesis is based on Primordial Life.

DeepMind Lab is a 3D learning environment based on id Software's Quake III Arena via ioquake3 and other open source software. DeepMind Lab provides a suite of challenging 3D navigation and puzzle-solving tasks for learning agents. Its primary purpose is to act as a testbed for research in artificial intelligence, especially deep reinforcement learning. If you use DeepMind Lab in your research and would like to cite the DeepMind Lab environment, we suggest you cite the DeepMind Lab paper...

Welcome to Spinning Up in Deep RL! This is an educational resource produced by OpenAI that makes it easier to learn about deep reinforcement learning (deep RL). For the unfamiliar, reinforcement learning (RL) is a machine learning approach for teaching agents how to solve tasks by trial and error. Deep RL refers to the combination of RL with deep learning. At OpenAI, we believe that deep learning generally, and deep reinforcement learning specifically, will play central roles in the development...

... by Hessel et al., n-step Bellman updates, prioritized experience replay, and distributional reinforcement learning. For completeness, we also provide an implementation of DQN (Mnih et al., 2015). For additional details, please see our documentation. We provide a set of Colaboratory notebooks which demonstrate how to use Dopamine. We provide a website which displays the learning curves for all the provided agents, on all the games.

Online Real Estate System (ORES) is web based Property Management Software that use to search, enter and edit property portfolios by Estate agents, customers or guests. ORES is beneficial to either a real estate agent or customers. This Property Management Software can be used to store and search the property portfolios. On the website, real estate agent can put the information regarding property portfolios. A general user or customer can browse such portfolios and later buy, sell or rent...

Web-controlled intelligent agents which interact with the Supply Chain Collaboration On-line Research Institute (http://www.sccori.com/sim/) supply chain simulation.

Socialscape is a tool for modeling artificial societies. Multiple agents move on a grid and interact with each other. Agents create value only by interacting with other agents, unlike “Sugarscape”, where agents get goods from the land.

An open-source desktop application for load/performance testing a web site. It has a very simple UI to configure the load test. The future plan includes transaction support, record, playback and support for load injector agents.

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.

sciSoccer is a framework to develop strategies for soccer playing robots like RobotCup. It is composed by libraries for robot communication, video capturing, image recognition, strategy implementation and a graphical user interface.

QASE is a Java-based API designed to provide all the functionality needed to create game agents in Quake 2. Powerful enough to facilitate high-end research, it is also suitable for undergrad courses geared towards classic AI and agent-based systems.

GnuTutor is an open source re-imagining of the intelligent tutoring system AutoTutor (autotutor.org) developed at the Institute for Intelligent Systems at the University of Memphis. GnuTutor has a simple codebase to foster development of derivative ITS.

This anonymous emailer script written in PHP is a free, opensource project designed to send EMails from anyone to anyone, with additional details such as Reply-To ,an anti-spam CAPTCHA and a WYSIWYG.

SAgent86 is the Java code for a participant agent in the Agent Reputation and Trust (ART) Testbed 0.3.4.

Springbots is a python application which takes a set of 2d physical structures built with nodes and movable springs and evolve them for specific tasks like walking, swimming and jumping using genetic algorithm.

Vehikel is a learning environment for behavior based control of mobile robots. A little bit artificial intelligence based on a domain specific language for the c't Bot.

This Java project creates a testing environment application to analyze an image at its low level features and suggest tags to clasify it using an ontology search based on the tags of similar images.

This is a bot programming game written in JAVA.You are required to write a program to control the player in a virtual environment to make the bot move, scan the arena for enemies, throw bombs etc. Two such programs are made to fight against each other.

A simulation environment for 2D robots to interact and perform tasks in. Meant to be educational and demonstrate emergent behaviors. No download necessary! See demos on project website!

The Robocode Depot is a web site and web service for sharing and finding information about Robocode robots for Robocode robot developers/competitors/competitions. It is deployed at: http://robocodedepot.net Implemented by using: Java, Wicket, Databinder

CAIR is an e-learning project that allow users and subjects management. You can associate pupils and teachers to subjects and works for this subjects. There are special functionalities for those subjects related to Robocup development.

SB-MASE is aimed at students and researchers in AI, for simulation and control of agents and robots. It uses task based decomposition and the subsumption architecture as its core control mechanisms and includes numerous possibilities for adding plug-ins.

Educational game framework supporting board games, strategy games, and other grid-based game boards. Currently uses Python/wxPython as the application language/library. C++ libs included to help create AI for the various games.