Multi-agent Reinforcement Learning in OpenSpiel: A Reproduction Report
This work incrementally verifies and documents existing methods for researchers using OpenSpiel, ensuring reliability and ease of reproduction.
The researchers reproduced core algorithms in the OpenSpiel framework for multi-agent reinforcement learning, validating their re-implementations against original results and providing full documentation for exact reproducibility.
In this report, we present results reproductions for several core algorithms implemented in the OpenSpiel framework for learning in games. The primary contribution of this work is a validation of OpenSpiel's re-implemented search and Reinforcement Learning algorithms against the results reported in their respective originating works. Additionally, we provide complete documentation of hyperparameters and source code required to reproduce these experiments easily and exactly.