Loading
Life sciences · Preprint
arXiv · September 3, 2026
Early or partial results. Treat as a signal, not a conclusion.
LUGL is a novel framework enabling gradient-boosted tree learners to operate in reinforcement learning settings by decoupling data collection from model fitting. Benchmark results on nine games are reported as competitive with or superior to neural network baselines (DQN, DeepCFR), but the work remains unreviewed and limited to game environments.
Computational methods study; controlled benchmark evaluation on nine game environments. Game-playing agents in nine standard benchmark environments (perfect and imperfect information games).. Intervention: LUGL framework using gradient-boosted trees (LightGBM) as the function approximator in RL setting.. Compared with: DQN and DeepCFR (neural network baselines)..
LightGBM-based agents achieve competitive or superior performance across all nine tested game benchmarks (four perfect-information, five imperfect-information games). LUGL framework enables non-incremental learners like gradient-boosted trees to operate in RL where distributional shift would otherwise prevent their use. Results reported as competitive with or superior to DQN and DeepCFR on Tic-tac-toe, Connect-4, Othello, Hex, Kuhn's poker, Leduc Hold'em, Liar's Dice, Goofspiel, and Flop5 Hold'em.
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
This is an unrefereed preprint presenting a novel algorithmic framework tested on benchmark games; the work is methodologically sound but lacks peer review, clinical or real-world validation, and independent replication.
As stated by the source record.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
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.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.