GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → nailo2c → a3c

nailo2c / a3c

Licence: other
PyTorch implementation of "Asynchronous advantage actor-critic"

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Labels

openai-gympytorcha3c

Projects that are alternatives of or similar to a3c

Tensorflow Rl
Implementations of deep RL papers and random experimentation
Stars: ✭ 176 (+738.1%)
Mutual labels:  openai-gym, a3c
Reinforcementlearning Atarigame
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
Stars: ✭ 118 (+461.9%)
Mutual labels:  openai-gym, a3c
Rl a3c pytorch
A3C LSTM Atari with Pytorch plus A3G design
Stars: ✭ 482 (+2195.24%)
Mutual labels:  openai-gym, a3c
tf-a3c-gpu
Tensorflow implementation of A3C algorithm
Stars: ✭ 49 (+133.33%)
Mutual labels:  openai-gym, a3c
Deep-Reinforcement-Learning-With-Python
Master classic RL, deep RL, distributional RL, inverse RL, and more using OpenAI Gym and TensorFlow with extensive Math
Stars: ✭ 222 (+957.14%)
Mutual labels:  openai-gym, a3c
A3c continuous
A continuous action space version of A3C LSTM in pytorch plus A3G design
Stars: ✭ 223 (+961.9%)
Mutual labels:  openai-gym, a3c
Btgym
Scalable, event-driven, deep-learning-friendly backtesting library
Stars: ✭ 765 (+3542.86%)
Mutual labels:  openai-gym, a3c
yarll
Combining deep learning and reinforcement learning.
Stars: ✭ 84 (+300%)
Mutual labels:  openai-gym, a3c
a3c-super-mario-pytorch
Reinforcement Learning for Super Mario Bros using A3C on GPU
Stars: ✭ 35 (+66.67%)
Mutual labels:  openai-gym, a3c
deep rl acrobot
TensorFlow A2C to solve Acrobot, with synchronized parallel environments
Stars: ✭ 32 (+52.38%)
Mutual labels:  openai-gym, a3c
gym-hybrid
Collection of OpenAI parametrized action-space environments.
Stars: ✭ 26 (+23.81%)
Mutual labels:  openai-gym
vizdoomgym
OpenAI Gym wrapper for ViZDoom enviroments
Stars: ✭ 59 (+180.95%)
Mutual labels:  openai-gym
jiminy
Jiminy: a fast and portable Python/C++ simulator of poly-articulated systems with OpenAI Gym interface for reinforcement learning
Stars: ✭ 90 (+328.57%)
Mutual labels:  openai-gym
FinRL
FinRL: The first open-source project for financial reinforcement learning. Please star. 🔥
Stars: ✭ 3,497 (+16552.38%)
Mutual labels:  openai-gym
Deep-Reinforcement-Learning-CS285-Pytorch
Solutions of assignments of Deep Reinforcement Learning course presented by the University of California, Berkeley (CS285) in Pytorch framework
Stars: ✭ 104 (+395.24%)
Mutual labels:  openai-gym
gym-line-follower
Line follower robot simulator environment for Open AI Gym.
Stars: ✭ 46 (+119.05%)
Mutual labels:  openai-gym
rl-bigwatermelon
用深度强化学习玩合成大西瓜
Stars: ✭ 22 (+4.76%)
Mutual labels:  a3c
distributed rl
Pytorch implementation of distributed deep reinforcement learning
Stars: ✭ 66 (+214.29%)
Mutual labels:  openai-gym
drl grasping
Deep Reinforcement Learning for Robotic Grasping from Octrees
Stars: ✭ 160 (+661.9%)
Mutual labels:  openai-gym
2048-Gym
This projects aims to use reinforcement learning algorithms to play the game 2048.
Stars: ✭ 68 (+223.81%)
Mutual labels:  openai-gym
View All Similar Projects ➔

a3c

使用PyTorch實作a3c演算法，參考了openai/universe-starter-agen以tensorflow實作的版本，以及ikostrikov/pytorch-a3c以PyTorch實作的版本。
以ikostrikov為主要參考，加上自行修改的一些部分，並以盡量精簡行數、寫出容易理解的code為目標。

Dependencies

  • Python 3.6
  • Anaconda
  • PyTorch
  • gym
  • gym[atari]
  • opencv-python

Getting Started

以下以Ubuntu 16.04 LTS環境為準，安裝Anaconda時請一路Enter與Yes到底。

wget https://repo.continuum.io/archive/Anaconda3-4.4.0-Linux-x86_64.sh
bash Anaconda3-4.4.0-Linux-x86_64.sh
source .bashrc
conda install pytorch torchvision -c soumith
conda install opencv
conda install libgcc
conda install -c conda-forge ffmpeg
pip install gym[Atari]
sudo apt-get update
sudo apt-get install -y python-numpy python-dev cmake zlib1g-dev libjpeg-dev xvfb libav-tools xorg-dev python-opengl libboost-all-dev libsdl2-dev swig

Rendering on a server

如果是跑在server上，需要依靠xvfb創造虛擬畫面支持rendering。

xvfb-run -s "-screen 0 1400x900x24" python main.py --env-name "Pong-v0" --num-processes 8

Architecture

Result

使用8顆cpu在GCP上跑2個小時。

References

Asynchronous Methods for Deep Reinforcement Learning
openai/universe-starter-agen
ikostrikov/pytorch-a3c

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].