Search Results for "agents"

Gym is a toolkit for developing and comparing reinforcement learning algorithms. It supports teaching agents, everything from walking to playing games like Pong or Pinball. Open source interface to reinforce learning tasks. The gym library provides an easy-to-use suite of reinforcement learning tasks. Gym provides the environment, you provide the algorithm. You can write your agent using your existing numerical computation library, such as TensorFlow or Theano. It makes no assumptions about...

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.

FRODO is a Java platform to solve Distributed Constraint Satisfaction Problems (DisCSPs) and Optimization Problems (DCOPs). It provides implementations for a variety of algorithms, including DPOP (and its variants), ADOPT, SynchBB, DSA...

... 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.

DisChoco is a Distributed Constraint Reasoning Solver. Several Distributed Constraint Reasoning algorithms are implemented (like ABT, AFC, Adopt, ...). Users may easily implement and test their algorithms with DisChoco. contact: wahbi[at]users[dot]sourceforge[dot]net

Critterding is a "Petri dish" universe in 3D that demonstrates evolving artificial life. Critters start out with completely random brains and bodies, but will automatically start evolving into something with much better survival skills.

AIS is an Development Platform providing a high-speed JIT compiler for LISP and JavaScript, web server, object repositories, MySQL integration and libraries supporting a wide variety of advanced genetic programming and symbolic regression techniques.

Search Agents - a framework for collaboration of meta-heuristic agents

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

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

This project aims to test Distributed Artifitial Intelligence in a urban traffic light control. GlobalSyncLocal is used to interact with the SUMO simulator through the TraSMAPI.

The JSparse Matrix Package, developed by Philipp Geigenmüller during an internship at the prudsys AG in Chemnitz, Germany, is an extension of the well-known Java Matrix Package (JAMA) and allows the use of sparse matrices and related algorithms.

This chess program changes its strength to give the best match against you. Eventually it learns to beat you specifically through learning alogirthms. Features included transposition tables and a elementary 3-piece endgame tablebase.

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++.

Animants are virtual ants. Their name comes from the combination of "ants" and "animats", an animat being "a sofware approximation of a living creature". Animants aim to simulate the behaviour of living animals.

Evolve is a simulation written in java that uses the Genetic Algorithm to evolve intelligent agents acting in a rich environment.

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 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!

This project intends to create an indexing search engine, for knowledge management. The primary object is to apply an information retrieval core. And implement a knowledge data discovery theory such as data mining algorithm, text mining.

The K.U.Leuven JCHR System is an integration of Constraint Handling Rules (CHR) and Java designed with three aims in mind: user-friendliness, flexibility and efficiency. http://www.cs.kuleuven.be/~petervw/JCHR/

Robot Warfare is a real-time strategy game that gives the user an opportunity to manage and program a team of battling robots that autonomously face opposing teams in a network-enabled environment.

PileWorks provides the organizational structure for coordinating several different projects which approach some aspect of Pile Technology. PileWorks defines a set of interfaces and implements some basic infrastructure for Pile engines and agents.

The Airs GPT project experiments with Steady State Genetic Programming create agents that play tag. It emphasises co-evolution through competition, and provides the user with some tools to help them visualize what is taking place.