Search Results for "learning"

...It is designed to play the board game Diplomacy by combining open-domain natural language negotiation with strategic planning. The repository includes training code, model checkpoints, and infrastructure for both language modelling (via the ParlAI framework) and reinforcement learning for strategy agents. It supports two variants: Cicero (which handles full “press” negotiation) and Diplodocus (a variant focused on no-press diplomacy) as described in the README. The codebase is implemented primarily in Python with performance-critical components in C++ (via pybind11 bindings) and is configured to run in a high‐GPU cluster environment. ...

A rudimentary 3D computer game that utilises artificial neural networks to enable computer agents to anticipate a target's location and shoot (bullets) in the corresponding direction.

nunn is a collection of ML algorithms and related examples written in modern C++17.

The Star Ships Learning Framework (SSLF) provides basic routines and methods in order to interact with the space shooter Star Ships V2.1. It provides the necessary interfaces for controlling the program's ships and its logic from outside the game.

SMILE = Speech & Music Interpretation by Large Space Extraction openSMILE is a fast, real-time (audio) feature extraction utility for automatic speech, music and paralinguistic recognition research developed originally at TUM in the scope of the EU-project SEMAINE, now maintained and supported by audEERING.

QtCritters is a simple critter simulation in C++ using Qt, currently under development. The goal of this project is to simulate a simple ecology of various kinds of animals, and to make the source easy to understand and modify. Still very very alpha...

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

This is my planning documentation and code for my thesis. The topic is learning from observation using the quake 2 and unreal tournament enviornments.

Artificial Intelligence Research & Development Project

The source code of the Brainstormers' RoboCup champion team 2005 has been made publicly available at the end of 2005. That source code release contains also a lot of our results in applying Reinforcement Learning in the simulated soccer domain.

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

Computer System for Adaptive Intelligent Life :: seeks to create a software system that is capable of learning. The project's ultimate goal is to further the ability of software to both adapt to individual users, and to respond their needs.

openEAR is the Munich Open-Source Emotion and Affect Recognition Toolkit developed at the Technische Universität München (TUM). It provides efficient (audio) feature extraction algorithms implemented in C++, classfiers, and pre-trained models on well-known emotion databases. It is now maintained and supported by audEERING. Updates will follow soon.

Machine Learning approach to Go

This is implementation of parallel genetic algorithm with "ring" insular topology. Algorithm provides a dynamic choice of genetic operators in the evolution of. The library supports the 26 genetic operators. This is cross-platform GA written in С++.

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.

a simple c/s framework software to play Reversi game also known as Othelo, with a well developed AI client, one could develop his/her own client too. Please refer to https://github.com/aijunbai/reversi.git for possible updates.

My Learning Assistant© (My LA)provides a set of middleware services for natural language question asking and answering to support an activity of individulized knowledge construction within game based learning environments

General purpose agents using reinforcement learning. Combines radial basis functions, temporal difference learning, planning, uncertainty estimations, and curiosity. Intended to be an out-of-the-box solution for roboticists and game developers.

The goal of the project it to learn how to use Neural Networks, and teach one how to play tic tac toe, and get to the never losing ability that most people can play at.