Skip to main content

A OpenAI Gym Env for discrete

Project description

gym-discrete

The domanin features a continuos state and a dicrete action space.

The environment initializes:

  • cross-sectional dataset with variables X_a, X_s, Y and N observations;
  • logit model fitted on the dataset, retrieving parameters \theta_0, \theta_1, \theta_2;

The agent:

  • sees a patient (sample observation);
  • predict his risk of admission \rho, using initialized parameters
  • sample an action (either 0 or 1)
  • if risk > 0.5 and action=1:
    • replace Xa by g, where g(\rho, Xa) is obtained using the patient's risk and Xa value
  • else:
    • do not intervene, X_a stays the same
  • give reward equal to average risk of admission, using predicted Y, initial parameters and sampled values

To install

git clone url-here cd gym-discrete

pip install gym-discrete import gym_discrete env =gym.make('discrete-v0')

To change version

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

gym_discrete-1.2.1.tar.gz (4.6 kB view hashes)

Uploaded Source

Built Distribution

gym_discrete-1.2.1-py3-none-any.whl (5.2 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page