Search Results for "jade multi agent"

Arcade Learning Environment (ALE) is a widely used open-source framework that wraps hundreds of Atari 2600 games via an emulator and presents them as RL environments for AI agents. It decouples the game/emulation aspects from the agent interface, providing a clean API (C++, Python, Gymnasium) so researchers can focus on agent design rather than game plumbing. This environment suite has been central to many RL breakthroughs, including value-based agents, deep Q-nets, and general-agent benchmarking, because the Atari games span many genres and present diverse learning challenges (pixels, actions, delayed rewards). ...

BrowserOS is an open-source, agentic web browser built on a Chromium base that integrates AI agents directly into the browsing experience. Rather than just doing standard browsing, it places AI intelligence at the core: you can connect your own API keys (for e.g., OpenAI, Anthropic, Google Gemini) or run local models (via e.g., Ollama) so that your browsing data and automation stay on your machine — privacy and control are emphasized throughout. The interface remains familiar to users of...

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games. OpenSpiel supports n-player (single- and multi- agent) zero-sum, cooperative and general-sum, one-shot and sequential, strictly turn-taking and simultaneous-move, perfect and imperfect information games, as well as traditional multiagent environments such as (partially- and fully- observable) grid worlds and social dilemmas. OpenSpiel also includes tools to analyze learning dynamics and other common evaluation metrics. ...

Fay is an open source framework designed to build and deploy interactive digital humans powered by large language models. It acts as a middleware layer that connects digital character technologies with conversational AI systems and business applications. Fay supports various types of digital humans, including 2.5D and 3D avatars, and can be integrated with applications running on mobile devices, PCs, web platforms, and embedded systems. Its architecture allows developers to combine different...

Library to help the creation of the dynamic systems, like simulators or games. Key word : 3D Rendering, Multi-Agent system, Collision detection, Game

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

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..).

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.

Zigorat is a base code for creating multi-agent intelligent systems fitting in robocup soccer simulator 3d, done and created by Zigorat AI Research Team.

Blackboard implements a lightweight, portable tuple space suitable for multi-agent system and distributed component design. Supports implicit invocation via content-filtered asynchronous events, blocking call semantics, and shared memory messaging.

MIC* comes with a new vision of multi-agent system engineering: The multi-agent system is devided explicitly into two dimensions: the deployment environment and the autonomous agents. MIC* is an algebraic model of a deployment environment (container of a

Mutli-Agent Communicating System.Based on an experiment carried out in the field of the videogame in the artificial intelligence,I board which been able to retain certain lesson of this work,and I would like to remake a Multi Agent System in Open Source.

(Multi-Agent) Transport Planner is (currently) a dynamic single agent transport planner for vehicle routing problems and dial-a-ride problems. MatPlan uses a (very quick) standard insertion technique to insert orders one by one into a set of routes.

The SLIE agent modelling software allows researchers in MAS (Multi-Agent Systems) to build simulations of MASes with a view to exploring design problems relating to scalability and robustness using techniques from ecology, biology and economics.

It helps multi-agent systems to achieve the teamwork.