PyTorch Implementation of REINFORCE for both discrete & continuous control
Switch branches/tags
Nothing to show
Clone or download
Latest commit 4a38741 Apr 16, 2017
Permalink
Failed to load latest commit information.
assets Add files via upload Apr 16, 2017
README.md Update README.md Apr 16, 2017
main.py support discrete Apr 16, 2017
normalized_actions.py v1 Apr 16, 2017
reinforce_continuous.py mean loss Apr 16, 2017
reinforce_discrete.py mean loss Apr 16, 2017

README.md

PyTorch REINFORCE

PyTorch implementation of REINFORCE.
This repo supports both continuous and discrete environments in OpenAI gym.

Requirement

  • python 2.7
  • PyTorch
  • OpenAI gym
  • Mujoco (optional)

Run

Use the default hyperparameters. (Program will detect whether the environment is continuous or discrete)

python main.py --env_name [name of environment]

Experiment results

continuous: InvertedPendulum-v1

discrete: CartPole-v0

Reference