Martin Riedmiller, Daan Wierstra, Ioannis Antonoglou, Alex Graves, David Silver, Koray Kavukcuoglu, Volodymyr Mnih - 2013

**Paper Links**: **Full-Text**

**Publications**: arXiv Add/Edit

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards. We apply our method to seven Atari 2600 games from the Arcade Learning Environment, with no adjustment of the architecture or learning algorithm. We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.

**Keywords**: Add/Edit

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

A very simple version of playing Atari with Deep Q Learning in caffe(python interface)

**Languages**: MoonScript Add/Edit

**Libraries**: Add/Edit

A powerful machine learning algorithm utilizing Q-Learning and Neural Networks, implemented using Torch and Lua.

**Languages**: Julia Add/Edit

**Libraries**: Add/Edit

Julia implementation of DeepMind's Deep Q Learning algorithm described in "Playing Atari with Deep Reinforcement Learning"

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Variation of "Asynchronous Methods for Deep Reinforcement Learning" with multiple processes generating experience for agent (Keras + Theano + OpenAI Gym)[1-step Q-learning, n-step Q-learning, A3C]

**Languages**: Lua Add/Edit

**Libraries**: Add/Edit

Persistent advantage learning dueling double DQN for the Arcade Learning Environment

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Implements basic reinforcement learning algorithms to control a remote-control car in a room.

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Re-implementation of method in Playing Atari with Deep Reinforcement Learning paper.

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

A reinforcement learning agent that uses Deep Q Learning with Experience Replay to learn how to play Pong.

**Languages**: C++ Add/Edit

**Libraries**: Add/Edit

Reproducing the results of "Playing Atari with Deep Reinforcement Learning" by DeepMind: Forked from kristjankorjus/Replicating-DeepMind

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Repository for all Honors Senior Thesis work. Research links and code should be kept here.

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Open source implementation of the PAAC algorithm presented in Efficient Parallel Methods for Deep Reinforcement Learning

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Implementation of "Playing Atari with Deep Reinforcement Learning" with Tensorflow

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

An implementation of Q algorithm and its deep variant for Reinforcement Learning purposes.

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

Diferentes aplicações de algoritmos de inteligência artificial (Machine Learning e Deep Learning).

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

This repository contains Deep Q-Networks and Double DQN implementation in tensorflow for Open AI Gym environments.

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Tensorflow implementation of deep Q networks in paper 'Playing Atari with Deep Reinforcement Learning'

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Implementation of Deep Q-Network (DQN) on OpenAI games: Pong and Breakout using Tensorflow and Numpy

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

Deep Q Learning model to play atari games based on the paper http://arxiv.org/pdf/1312.5602v1.pdf