david-simoes-93/A3C3

This repository has been archived on 04/Jun/2021
Stars
16
Rank 1,311,288 (Top 26 %)
Language
Python
Created almost 6 years ago
Updated over 3 years ago

david-simoes-93/A3C3

david-simoes-93

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

A deep reinforcement learning multi-agent algorithm, where a team learns to complete a task and communicate between agents.

Mixed-Policy-Asynchronous-Deep-Q-Learning

Deep learning implementations (Asynchronous Deep Q-Learning) of multiple Game Theory algorithms for adversarial learning (WoLF-PHC, GIGA-WoLF, WPL, EMA-QL, PGA-APP)

Multi-agent-Double-Deep-Q-Networks

A multi-agent version of the Double DQN algorithm, with Foraging Task and Pursuit Game test scenarios

A3C2

Asynchronous Advantage Actor-Critic with Communication

UsefulPi

Lots of small utilities and snippets to use on a Raspberry Pi!

RCSoccerSim3dSetup

DistributedAtariQLearning

A Distributed TensorFlow implementation of Atari Reinforcement Learning with n-step Q-learning and Q-batch

ArcadePi

A system to play MS-DOS, Sega, Win98 or any other videogame using arcade controllers and a DYI arcade station!

IMDBIndexer

A graphical media manager, using OMDB to catalogue movies in different playlists.

SpaceInvaders

The classic arcade game!

GeoFriends2

An OpenAI Gym environment with complex puzzle maps, highly adequate for reinforcement learning approaches.

GeoFriends2-v2

A modular re-implementation of GeoFriends2, a Gym-compliant multi-agent environment, ideal for reinforcement learning.

SH17

Sunset Hackathon 2017