aiqbench analysis
This study validates the efficacy of adaptive AI methods, specifically evolutionary transfer learning and TD(lambda), within the structurally complex domain of Dragonchess. By optimizing the engine implementation to C++, researchers enabled rigorous statistical testing over 10,000 games, demonstrating that these techniques successfully update evaluation heuristics in novel environments without significant performance variance between evolved and learned approaches.
Temporal-Difference Learning for Dragonchess
arXiv:2610.01845v1 Announce Type: new Abstract: Our research investigates how two adaptive AI methods, evolutionary transfer learning and TD(lambda), perform in the three-dimensional chess environment Dragonchess. The game challenges players with its unique board structure and computational load, making it an ideal setting to study how adaptive methods can update evaluation heuristics in novel environments. In this work we re-implement the Dragonchess engine, changing it from a PyGame engine to C++. This enables faster gameplay, allowing us to run 10,000 games with confidence intervals and significance tests, rather than a single small tournament. Both adaptive methods outperform all other agents in the round-robin tournament. Our results showed that there is no significant difference in the performance between the evolved and learned evaluations. This research establishes the efficacy of adaptive methods in structurally complex, novel game domains.
Abstract:Our research investigates how two adaptive AI methods, evolutionary transfer learning and TD(lambda), perform in the three-dimensional chess environment Dragonchess. The game challenges players with its unique board structure and computational load, making it an ideal setting to study how adaptive methods can update evaluation heuristics in novel environments. In this work we re-implement the Dragonchess engine, changing it from a PyGame engine to C++. This enables faster gameplay, allowing us to run 10,000 games with confidence intervals and significance tests, rather than a single small tournament. Both adaptive methods outperform all other agents in the round-robin tournament. Our results showed that there is no significant difference in the performance between the evolved and learned evaluations. This research establishes the efficacy of adaptive methods in structurally complex, novel game domains.
Artificial Intelligence (cs.AI)
arXiv:2610.01845 [cs.AI]
(or arXiv:2610.01845v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.01845 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 224 words
Related coverage
TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting
arXiv · Oct 15, 2026
Generalized Kalman filter based temporal difference reinforcement learning
arXiv · Jul 23, 2026
Frame-Level Temporal Alignment for Human-to-Robot Visual Adaptation
arXiv · Oct 6, 2026
Stochastic Siamese MAE Pretraining for Longitudinal Medical Images
arXiv · Oct 7, 2026