Jordan Terry, CEO of Farama Foundation and Swarm Labs

Abstract:

To conclude our summer series on MARL research techniques, Jordan Terry will give a demonstration of PettingZoo and Umshini on August 22nd. PettingZoo is a simple, pythonic interface capable of representing general multi-agent reinforcement learning (MARL) problems. PettingZoo includes a wide variety of reference environments, helpful utilities, and tools for creating your own custom environments. PettingZoo environments can be integrated into Umshini, which is an upcoming unreleased framework for testing RL games. Unlike other options, submissions are straightforward (two lines of code!) and competitions can be run regularly.

This talk will have an interactive session component.