Giter Site home page Giter Site logo

bbruhh / deeprl_practice_colab Goto Github PK

View Code? Open in Web Editor NEW

This project forked from kaist-ailab/deeprl_practice_colab

0.0 1.0 0.0 9.6 MB

Preparation for Deep Reinforcement Learning using Google Colab

Jupyter Notebook 11.55% Python 83.75% Dockerfile 0.13% Makefile 0.43% Ruby 0.71% Mako 0.22% Shell 0.22% CSS 0.48% JavaScript 1.64% HTML 0.87%

deeprl_practice_colab's Introduction

Deep Reinforcement Learning Practice with Google Colab

Day 1: Value-Based RL

Day 2: Policy-Based RL

Day 3: Transfer Learning

  • 실습 교육 내용:
  • 실습 내용 (못하면 숙제):
    • Tensorflow로 구현된 MAML을 Theano로 구현.

Preparation Progress

  1. Colab에서 anaconda env로 rllab 실행하는걸 마무리. Anaconda 안 쓰고, CUDNN을 따로 깔아서 GPU로 rllab 코드를 돌릴 수 있 colab ipython notebook도 따로 만듬.
  2. learned parameter, average return 저장 옵션 어떻게 주는지 확인 (trpo_cartpole.py, trpo_swimmer.py)
  3. iteration 별로 average return plot (pyplot) (trpo_cartpole.py, trpo_swimmer.py)
  4. code 블록 의미 있게 나눠서 따로 실행 가능하게 colab에 써보기
  5. distral, maml 분석. rllab 사용 가능한지 보기.. (내 기억에는 maml rllab으로 구현됐던거 같음)
  6. env observation normalization function 수정 (거의 모든 알고리즘에 적용되기 때문에 수정해야 함) (교수님 rllab파일 사용) (baselines, rllab trpo가 같은 성능을 보이게)
  7. gym environment에 video recording=True옵션 줘서 님mp4 저장하는 것 시도해볼 것
  8. DQN+, DQN++, MAML 코드 돌려보고 colab에 추가

deeprl_practice_colab's People

Contributors

haanvid avatar gr8joo avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.