Hearts GymΒΆ

This is the documentation for Hearts Gym.

The main documentation file is Hearts Gym Documentation. It contains instructions on getting started, configuration, development, and others. The other documents are more specific in their focus.

Contents:

  • Hearts Gym Documentation
    • Introduction
    • Installing
      • Environment Setup
      • Installing Requirements
      • Conda Installation
    • Usage
      • Training
      • Evaluation
      • Configuration
      • Rule-based Agents
      • Development
    • Miscellaneous Information
      • Supported Algorithms
      • Notes on Action Masking
      • Notes on Auto-Wrapping and Action Masking
      • Sharing Checkpoints
      • Monitoring Training with TensorBoard
      • Security
    • References
  • Hearts Environment
    • Observations
      • Cards
      • Leading Hearts Allowed
      • Action Mask
    • Actions
      • Illegal Actions
  • Reward Shaping
    • Useful Variables and Functions available to RewardFunction
  • Rule-based Policies
    • Implementing the Default Rule-based Policy
      • Observed Games
    • Implementing Other Rule-based Policies
  • Client-Server Interaction
    • Need-to-Knows
    • Order of Communication
  • Feature Engineering
  • Search Page

Hearts Gym

Navigation

  • Hearts Gym Documentation
  • Hearts Environment
  • Reward Shaping
  • Rule-based Policies
  • Client-Server Interaction
  • Feature Engineering

Related Topics

  • Documentation overview
    • Next: Hearts Gym Documentation

Quick search

©2022, Jan Ebert. | Powered by Sphinx 5.0.0 & Alabaster 0.7.12 | Page source