PantheonRL: A MARL Library for Dynamic Training Interactions

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