A3C-Tensorflow

Simple Example A3C Reinforcement Learning Algorithm in Tensorflow

Stars

11

View Code on GitHub

Ecosystems: Python

Asynchronous Methods for Deep Reinforcement Learning (A3C)

A3C implementation in TensorFlow
There are two versions
- A3C using threads
- A3C using distributed tensorflow
Tested on "Pong-v0" which is a stochastic environment due to random frame skipping
Original paper: https://arxiv.org/abs/1602.01783

Tensorboard

Episode length

The time length of an episode increases as it starts to play neck and neck against the AI
After an hour, the trained agent begins to beat the AI easily

Episode reward

The maximum score possible is 21

Related Projects

Deep-Reinforcement-Learning-Algorithms-with-PyTorch

PyTorch implementations of deep reinforcement learning algorithms and environments

07 Sep 2018 5,584

async-rl

Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods f...

14 Apr 2016 1,012

softlearning

Softlearning is a reinforcement learning framework for training maximum entropy policies in conti...

03 Dec 2018 1,200

DeepLearningVideoGames

03 Nov 2015 1,075

awesome-google-colab

Google Colaboratory Notebooks and Repositories (by @firmai)

11 Nov 2019 1,363

reinforcement-learning-an-introduction

Python Implementation of Reinforcement Learning: An Introduction

13 Sep 2016 13,499

DeepRL-Tutorials

Contains high quality implementations of Deep Reinforcement Learning algorithms written in PyTorch

31 May 2018 1,053

Super-mario-bros-A3C-pytorch

Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros

29 May 2019 1,035

rlpyt

Reinforcement Learning in PyTorch

28 Apr 2019 2,221

king-pong

Deep Reinforcement Learning Pong Agent, King Pong, he's the best

genrl

A PyTorch reinforcement learning library for generalizable and reproducible algorithm implementat...

26 Mar 2020 403

car-racing-attention-agent

Reproduce the results of "Neuroevolution of Self-Interpretable Agents" paper

tiny-dqn

A tiny implementation of Deep Q Learning, using TensorFlow and OpenAI gym

DQN-tensorflow

Tensorflow implementation of Human-Level Control through Deep Reinforcement Learning

15 May 2016 2,475

rl-examples

Examples of published reinforcement learning algorithms in recent literature implemented in Tenso...