Metraipolis › archive › dc_bb6572e75d40
Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners — arXiv:2609.03660
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03660
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:12:02.251Z
- SHA-256 of the archived text
c835986c54fe0e73a6704a39ac99677de93790c71e3ef7814e5256332be48769- Stable URL of this page
https://metraipolis.com/documento/dc_bb6572e75d40
How to cite
Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners — arXiv:2609.03660 — arXiv (en), https://arxiv.org/abs/2609.03660 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb6572e75d40 (Metraipolis archive dc_bb6572e75d40, sha256 c835986c54fe0e73a6704a39ac99677de93790c71e3ef7814e5256332be48769)
BibTeX
@misc{dcbb6572e75d40,
title = {Local Updates, Global Learning (LUGL): Playing Games with non-incremental Learners — arXiv:2609.03660},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03660},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb6572e75d40; sha256 c835986c54fe0e73a6704a39ac99677de93790c71e3ef7814e5256332be48769},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03660. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The dominance of Neural Networks (NNs) in RL is partially due to their incremental learning capability, which naturally suits the online, non-stationary nature of self-play training. However, gradient-boosted trees like LightGBM are widely recognised as the state of the art for tabular data in supervised learning, often outperforming NNs in accuracy and efficiency. Game states are inherently tabular---discrete actions, categorical card identities, structured board positions---which makes them an ideal candidate for tree-based methods. We introduce LUGL (Local Updates, Global Learning), a framework that decouples data collection from model fitting, enabling non-incremental learners such as GBTs to operate in RL settings where they would otherwise fail due to distributional shift. LUGL alternates between a local updates phase, where the agent plays self-play games and accumulates tabular updates (Q-values, V-values, policies, or regret values) in a finite table, and a global learning phase, where the table is used to train a function approximator that generalises to unseen states before the table is reset. We test our approach in four standard perfect-information games (Tic-tac-toe, Connect-4, Othello, and Hex) and five imperfect-information games (Kuhn's poker, Leduc Hold'em, Liar's Dice, Goofspiel, and Flop5 Hold'em), and show that our results are competitive with or superior to DQN and DeepCFR. Our experiments demonstrate that the community's strong bias towards NNs in game-playing may be unwarranted, since LightGBM-based agents achieve competitive or superior performance across all tested benchmarks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.03660 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T00:28:02.992Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).