Co-Learning Empirical Games & World Models

Max Olan Smith, Michael P. Wellman

Primary Area: reinforcement learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Multiagent learning, Empirical Game Theory, Model-Based Reinforcement Learning, Transfer Learning

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: Co-learning world models and empirical games jointly improves each, and leads to more efficient game-solving.

Abstract:

Game-based decision-making involves reasoning over both world dynamics and strategic interactions among the agents.
Typically, empirical models capturing these respective aspects are learned and used separately.
We investigate the potential gain from co-learning these elements: a world model for dynamics and an empirical game for strategic interactions.
Empirical games drive world models toward a broader consideration of possible game dynamics induced by a diversity of strategy profiles.
Conversely, world models guide empirical games to efficiently discover new strategies through planning.
We demonstrate these benefits first independently, then in combination as realized by a new algorithm, Dyna-PSRO, that co-learns an empirical game and a world model.
When compared to PSRO---a baseline empirical-game building algorithm, Dyna-PSRO is found to compute lower regret solutions on partially observable general-sum games.
In our experiments, Dyna-PSRO also requires substantially fewer experiences than PSRO, a key algorithmic advantage for settings where collecting player-game interaction data is a cost-limiting factor.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3944