Koray Kavukcuoglu, David Silver, Tim Harley, Timothy P. Lillicrap, Alex Graves, Mehdi Mirza, Adri Puigdomnech Badia, Volodymyr Mnih - 2016

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

**Publications**: arXiv Add/Edit

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing all four methods to successfully train neural network controllers. The best performing method, an asynchronous variant of actor-critic, surpasses the current state-of-the-art on the Atari domain while training for half the time on a single multi-core CPU instead of a GPU. Furthermore, we show that asynchronous actor-critic succeeds on a wide variety of continuous motor control problems as well as on a new task of navigating random 3D mazes using a visual input.

**Keywords**: Add/Edit

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Implementation of Asynchronous Methods for Deep Reinforcement Learning in TensorFlow + OpenAI Gym

**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**: Python Add/Edit

**Libraries**: Add/Edit

A Tensorflow based implementation of "Asynchronous Methods for Deep Reinforcement Learning": https://arxiv.org/abs/1602.01783

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Tensorflow implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Examples of published reinforcement learning algorithms in recent literature implemented in TensorFlow

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

A pytorch implementation of LSTM cell with a differentiable neural dictionary, based on Ritter et al. (2018). Been There, Done That: Meta-Learning with Episodic Recall.

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Modified tensorflow implementation of 'Asynchronous Methods for Deep Reinforcement Learning'

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Replicating "Asynchronous Methods for Deep Reinforcement Learning" (http://arxiv.org/abs/1602.01783)

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Using a paper from Google DeepMind I've developed a new version of the DQN using threads exploration instead of memory replay as explain in here: http://arxiv.org/pdf/1602.01783v1.pdf I used the one-step-Q-learning pseudocode, and now we can train the Pong game in less than 20 hours and without any GPU or network distribution.

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

Pytorch LSTM RNN for reinforcement learning to play Atari games from OpenAI Universe. We also use Google Deep Mind's Asynchronous Advantage Actor-Critic (A3C) Algorithm. This is much superior and efficient than DQN and obsoletes it. Can play on many games

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

Teaching materials for the seminar on Application of Computational Intelligence Methods

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Tensorflow implementation of asyncronous 1-step Q learning in "Asynchronous Methods for Deep Reinforcement Learning" with improvement on weight update process (use minibatch) to speed up training.

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Tensorflow implementation of 'Asynchronous Methods for Deep Reinforcement Learning'

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Implementation of asynchronous n-step Q-learning from Deepmind's "Asynchronous Methods for Deep Reinforcement Learning"

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Implementing Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning". using TensorFlow

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

An implementation of the Asynchronous Advantage Actor Critic (A3C) algorithm for any environment

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Implementation of "Asynchronous Methods for Deep Reinforcement Learning" by Deep Mind

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

This repo demonstrates the usage of an actor-critic setup via the deep-deterministic-policy-gradients algorithm. The environment to be solved is the Unity Reacher Environment provided in the Udacity Deep Reinforcement Learning nanodegree

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

An implementation of a DQN to play Space Invaders using TensorFlow and Open-AI gym

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

N-Layered FeUdal Networks based on FeUdal Networks adapted to suit PySC2 observations

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Training a DRL agent to play Flappy Bird. An exercise to reimplement DQN, A2C, and PPO DRL methods.

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

PyTorch implementation of Advantage async actor-critic Algorithms (A3C) in PyTorch

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

Implementation of Asynchronous methods for deep reinforcement learning Breakout

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

Training a DRL agent to play Flappy Bird. An exercise to reimplement DQN, A2C, and PPO DRL methods.

**Languages**: Jupyter Notebook Add/Edit

**Libraries**: Add/Edit

1-step Q Learning from the paper "Asynchronous Methods for Deep Reinforcement Learning"

**Languages**: Python Add/Edit

**Libraries**: Add/Edit

MXNET + OpenAI Gym implementation of A3C from "Asynchronous Methods for Deep Reinforcement Learning"