entity-gym 0.1.1

Entity Gym

Entity Gym

Entity Gym is an open source Python library that defines an entity based API for reinforcement learning environments. Entity Gym extends the standard paradigm of fixed-size observation spaces by allowing observations to contain dynamically-sized lists of entities. This enables a seamless and highly efficient interface with simulators, games, and other complex environments whose state can be naturally expressed as a collection of entities.

The ENN-PPO library can be used to train agents for Entity Gym environments.

Installation

pip install entity-gym

Usage

• The Quick Start Guide walks you through the process of implementing and running a simple grid-world environment.
• The Advanced Tutorial goes into additional detail about environments in which the agent controls multiple entities.

Examples

A number of simple example environments can be found in entity_gym/examples. The ENN-Zoo project implements Entity Gym bindings for Procgen, Griddly, MicroRTS, VizDoom, and CodeCraft.

API Reference

TODO