hippogym


Keywords
gym, human, loop, reinforcement, learning
License
Apache-2.0
Install
pip install hippogym==2.0.0a2

Documentation

HippoGym

Human Input Parsing Platform for Openai Gym

Fury - PyPi stable version PePy - Downloads PePy - Downloads per week

Codacy - grade Codacy - coverage CodeStyle - Black CodeStyle - Ruff

Purpose:

HippoGym is a python library for simplifying human-ai interaction research over the web. The library provides a communicator that opens a websocket to pass environment information and recieve commands and actions from browser-based front-end.

The library is designed to be customizable for diverse research applications. The framework is naive in that it makes no assumptions about how human or agents input will be used, it simply provides the mechanism to pass along and record this information.

Installation

pip install hippogym

Examples

Lunar Lander with human agent

Copy and run the lunar lander example.

You should see: Backend log success lunar

Then connect a client to the websocket using the host and port, you can use the irll frontend: https://beta.irll.net/?server=ws://localhost:5000

You can now play with either the command pannel or the keyboard: Frontend display lunar

Minigrid with human agent

Copy and run the minigrid example.

You should see: Backend log success minigrid

Then connect a client to the websocket using the host and port, you can use the irll frontend: https://beta.irll.net/?server=ws://localhost:5000

You can now play with either the command pannel or the keyboard: Frontend display minigrid