PantheonRL: A MARL Library for Dynamic Training Interactions

TL;DR

PantheonRL is a flexible multiagent reinforcement learning library that supports various dynamic training interactions, integrates with existing RL algorithms, and provides an easy-to-use web interface for experiment management.

Contribution

It introduces a versatile multiagent RL library with configurable interactions, built on StableBaselines3, and includes a user-friendly web interface for experiment setup.

Findings

Supports diverse multiagent training interactions

Integrates seamlessly with existing RL algorithms

Provides an intuitive web interface for experiments

Abstract

We present PantheonRL, a multiagent reinforcement learning software package for dynamic training interactions such as round-robin, adaptive, and ad-hoc training. Our package is designed around flexible agent objects that can be easily configured to support different training interactions, and handles fully general multiagent environments with mixed rewards and n agents. Built on top of StableBaselines3, our package works directly with existing powerful deep RL algorithms. Finally, PantheonRL comes with an intuitive yet functional web user interface for configuring experiments and launching multiple asynchronous jobs. Our package can be found at https://github.com/Stanford-ILIAD/PantheonRL.