Git Product home page Git Product logo

ddpg-mountain-car-continuous's Introduction

Continuous control with deep reinforcement learning

Hits

  • Implement DDPG ( Deep Deterministic Policy Gradient)

Experiments

Game Epochs Training Time Model Parameters
MountainCarContinuous-v0 1000 30 min 299,032(total)
Pendulum-v0 1000 30 min 299,536(total)
3DBall willbeupdated willbeupdated willbeupdated

Todo

  • solve the problem that if epochs are over 200, then the action is converged in wrong direction.
  • more games have to be tested.
  • parser

Update (2019.08.27)

  1. Save error and notation fixed
  2. argparser added

Update (2019.08.30)

  1. replaybuffer.py's sampling method is changed.
  2. new test result added.
  3. pendulum-v0 is now testing.

Plot

MountainCarContinuous-v0

2019.08.27

img

  • As epochs over 200, all(train and test) models are diverged.
    • i tried to adjust batch size, learning-rate, activation function, model size, noise size but it is not cleared.
2019.08.30

img

  • it doesn't converged at all.
    • i tried almost same model maded by another people, it looks same i guess here, but it looks converged. but my model didn't converged.
2019.08.30

img

  • i changed the training rate in Critic model at 0.001 to 0.0001(i have tried some points.)
    • it shows that model can be trained well by adjusting the learning rate. i gain the idea from TRPO and PPO that the change of model of parameters is handled carefully.

Run

python main.py
  • If you want to change hyper-parameters, you can check "python main.py --help"

Options:

  • '--epochs', type=int, default=100, help='number of epochs, (default: 100)'
  • '--e', type=str, default='MountainCarContinuous-v0', help='environment name, (default: MountainCarContinuous-v0)' #- '--d', type=bool, default=False, help='train and test alternately. (default : False)'
  • '--t', type=bool, default=True, help="True if training, False if test. (default: True)"
  • '--r', type=bool, default=False, help='rendering the game environment. (default : False)'
  • '--b', type=int, default=128, help='train batch size. (default : 128)'
  • '--v', type=bool, default=False, help='verbose mode. (default : False)' #- '--n', type=bool, default=True, help='reward normalization. (default : True)'
  • '--sp', type=int, default=True, help='save point. epochs // sp. (default : 100)'

Reference

Version

ddpg-mountain-car-continuous's People

Watchers

 avatar

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.