Search Results for "artificial intelligence algorithm" - Page 4

Highly modularized Reinforcement Learning library for real/simulation robots to learn behaviors. Our ultimate goal is to develop an artificial intelligence (AI) program with which the robots can learn to behave as their users wish.

Adaptive Synchronous-Retrieval mechanism with Concurrent I/O using Reinforcement Learning. A data retrieval mechanism that can adapt to the continuous contraction and expansion of the network bottleneck so that an optimal concurrency index can be maintained at any time during the data retrieval process. Sample usage: python iget.py <target url> <output file>

Based on the rl-ggp project. Research & development project on General Game Playing and relational reinforcement learning.

Closed Loop Simulation System (CLSquare) is an integrated architecture to train, test and compare reinforcement learning controllers on different plants. CLSquare provides simulated plants as well as interfaces to real plants.

This project contains the files required to run the Cross-Entropy Relational Reinforcement Learning Agent (CERRLA) algorithm. Note that a copy of the JESS rules engine will also be required.

This Java-application contains all required components to simulate a game of Ms. Pac-Man and let an agent learn intelligent playing behaviour using reinforcement learning and either Q-Learning or SARSA. The framework was developed by Luuk Bom and Ruud Henken, under supervision of Marco Wiering, Department of Artificial Intelligence, University of Groningen. It formed the basis of a bachelor's thesis titled "Using reinforcement learning with relative input to train Ms. Pac-Man", L.A.M. Bom...

This project provides a framework for testing and comparing different machine learning algorithms (particularly reinforcement learning methods) in different scenarios. Its intended area of application is in research and education.

Reinforcement learning and simulation-based search in computer Go

Parallel Reinforcement Evolutionary Artificial Neural Networks (PREANN) is a framework of flexible multi-layer ANN's with reinforcement learning based on genetic algorithms and a parallel implementation (using XMM registers and NVIDIA's CUDA).

A project to compare classic reinforcement learning algorithms on the Pong game.

Learning NLG template parameter types with reinforcement learning.

In this Project, We solved 8-puzzle problem, very famous problem in AI, by using reinformcemnt learning concepts.

Algorithms in Reinforcement Learning: An Introduction (Sutton and Barto)

Using reinforcement learning in neural network for learning othello

Agents based reinforcement learning using Mathematica

This is a third year computer science project. A software system for simulating and animating Reinforcement Learning (RL) algorithms mainly for modular robots.

The Free Connectionist Q-learning Java Framework is an library for developing learning systems. Keywords: qlearning, artificial intelligence, alife, neural nets, neural networks, machine learning, reinforcement learning unsupervised learning agents lejos

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

PIQLE is a Platform Implementing Q-LEarning (and other Reinforcement Learning) algorithms in JAVA. Version 2 is a major refactoring. The core data structures and algorithms are in piqle-coreVersion2. Examples are in piqle-examplesVersion2. A complete doc

RL Poker is a study project Java implementation of an e-soft on-policy Monte Carlo Texas Hold'em poker reinforcement learning algoritm with a feedforward neural network and backpropagation. It provides a graphical interface to monitor game rounds.

A general purpose reinforcement learning engine.

The ultimate Reinforcement Learning Simulator!!!

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.

RL++ is an easy to use modular open source library for Reinforcement Learning written in C++. It includes learning algorithms (TD, Sarsa, Q) as well as the implementation of value function representations (LookupTable, TileCoding, Neuronal Network).

The Chevrolett project tries to construct Agents based on Reinforcement Learning.