tiagoCuervo / PPO-harvest

Proximal Policy Optimization algorithm applied to the Harvest Game, a multi-agent environment

This is an implementation of the Proximal Policy Optimization algorithm applied to the Commons Game, a multi-agent environment proposed in A multi-agent reinforcement learning model of common-pool resource appropriation.

Requirements

• Pytorch 1.4
• The Commons Game gym environment: https://github.com/tiagoCuervo/CommonsGame

Usage

The file example.py contains an usage example.