pytorch-ddpg

by ghliu

Implementation of the Deep Deterministic Policy Gradient (DDPG) using PyTorch

241 Stars 79 Forks Last release: Not found Apache License 2.0 15 Commits 0 Releases

Available items

No Items, yet!

The developer of this repository has not created any items for sale yet. Need a bug fixed? Help with integration? A different license? Create a request here:

======

Deep Deterministic Policy Gradient on PyTorch

Overview

The is the implementation of

Deep Deterministic Policy Gradient 
_ (DDPG) using
PyTorch 
. Part of the utilities functions such as replay buffer and random process are from
keras-rl 
repo. Contributes are very welcome.

Dependencies

  • Python 3.4
  • PyTorch 0.1.9
  • OpenAI Gym 
    _

Run

  • Training : results of two environment and their training curves:

    • Pendulum-v0

    .. code-block:: console

    $ ./main.py --debug
    

    .. image:: output/Pendulum-v0-run0/validate_reward.png :width: 800px :align: left :height: 600px :alt: alternate text * MountainCarContinuous-v0

    .. code-block:: console

    $ ./main.py --env MountainCarContinuous-v0 --validate_episodes 100 --max_episode_length 2500 --ou_sigma 0.5 --debug
    

    .. image:: output/MountainCarContinuous-v0-run0/validate_reward.png :width: 800px :align: left :height: 600px :alt: alternate text

  • Testing :

.. code-block:: console

$ ./main.py --mode test --debug

TODO

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.