Giter Site home page Giter Site logo

seungjaeryanlee / playing-hard-exploration-games-by-watching-youtube Goto Github PK

View Code? Open in Web Editor NEW
12.0 4.0 3.0 509 KB

[WIP] Playing Hard Exploration Games by Watching YouTube (Aytar et al., 2018)

License: MIT License

Jupyter Notebook 89.60% Python 10.14% Shell 0.26%
python python3 pytorch deep-learning reinforcement-learning deep-reinforcement-learning deepmind

playing-hard-exploration-games-by-watching-youtube's Introduction

Playing Hard Exploration Games by Watching YouTube

black Build Status flake8 Build Status isort Build Status mypy Build Status

numpydoc Docstring Style pre-commit

A PyTorch implementation of Playing Hard Exploration Games by Watching YouTube (Aytar et al., 2018)

Installation

First, install FFMPEG for skvideo.io.

sudo apt-get install ffmpeg

Then, install Python packages using requirements.txt.

pip install -r requirements.txt

Download Video and Audio

To train TDC and CMC, you need videos and audios. Because of their size, they are not included in the repository.

Running get_av.sh should automatically download and extract video and audio to data/. You can also download them from my public Google Drive folder.

Download Pretrained Embedders

I have saved TDC and CMC networks that have been trained with videos above. Because of their size, they are not included in the repository.

Running get_pretrained_models.sh should automatically download saved parameters to saves/. You can also download them from my public Google Drive folder.

playing-hard-exploration-games-by-watching-youtube's People

Contributors

seungjaeryanlee avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar

playing-hard-exploration-games-by-watching-youtube's Issues

Got runtime error

When I run "retrain-embeddings.py", I got:

RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 12 and 9 in dimension 1 at /Users/soumith/b101_2/2019_02_08/wheel_build_dirs/wheel_3.7/pytorch/aten/src/TH/generic/THTensorMoreMath.cpp:1307

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.