Search Results for "agent" - Page 3

MADDPG (Multi-Agent Deep Deterministic Policy Gradient) is the official code release from OpenAI’s paper Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. The repository implements a multi-agent reinforcement learning algorithm that extends DDPG to scenarios where multiple agents interact in shared environments. Each agent has its own policy, but training uses centralized critics conditioned on the observations and actions of all agents, enabling learning in cooperative, competitive, and mixed settings. ...

Coach is a python framework that models the interaction between an agent and an environment in a modular way. With Coach, it is possible to model an agent by combining various building blocks, and training the agent on multiple environments. The available environments allow testing the agent in different fields such as robotics, autonomous driving, games and more. It exposes a set of easy-to-use APIs for experimenting with new RL algorithms and allows simple integration of new environments to solve. ...

The purpose of the project is to develop a portable programming framework that facilitates distributed and multi-threaded programming for C++, Java, and Python. MADARA was originally developed as an agent-based middleware specifically for real-time, distributed artificial intelligence, but is now more general purpose for distributed timing, control, knowledge and reasoning, and quality-of-service. MADARA is composed of several tools and middleware, and the main entry point into the system is the Knowledge and Reasoning Language (KaRL) Engine, which provides a real-time scripting language for nanosecond execution times hooked into a flexible transport layer for distributed reasoning. ...

Spyse is a software framework for building multi-agent systems. It allows Python developers to build distributed intelligent systems of multiple cooperative agents based on FIPA, OWL, SOA and many others. Spyse is designed for ease-of-use and fun.

OSE is a C++ library, with some Python wrappers, containing generic classes, as well as support for event driven systems, interprocess communications and a request/reply, publish/subscribe service agent framework with RPC over HTTP interface.

FEAR is a development kit helping software engineers create advanced artificial intelligence in synthetic characters with simplicity and efficiency. The project includes reusable AI components, portable framework and interfaces to realtime 3D games.

java-based complete Agent (Artificial Intelligence) Framework with all the features you might expect in an Agent Framework: Mobility, Autonomy, Distributed communication, Agents can be written in Java, Jython, or Beanshell.

Open_PYOSS will be a platform to develop Operational Support Systems for the Cable MSO. It will capitalized on a Distributed NxTier Computing Agent environment and WebServices core technologies to provide seamless Managed Access for MSOs or xSPs

Infrastructure for autonomous agents, written in Python.

Jacomma is a framework for developing network-aware reactive information agents, using the ICM agent communication infrastructure. It offers transparent ICM bindings for java, and includes a lightweight agent execution environment.