Researchers have developed a new framework called LUGL (Local Updates, Global Learning) that allows non-incremental learners, such as gradient-boosted trees (GBTs), to be effectively used in reinforcement learning (RL) settings. This approach decouples data collection from model fitting, enabling GBTs to overcome the distributional shift issues that typically hinder their use in RL. LUGL alternates between accumulating tabular updates in a finite table and using this table to train a generalizable function approximator. Experiments across various perfect and imperfect-information games show that LUGL, particularly with LightGBM, achieves performance competitive with or superior to established methods like DQN and DeepCFR, challenging the prevailing reliance on neural networks for game-playing AI. AI
IMPACT Challenges the dominance of neural networks in game-playing AI and suggests gradient-boosted trees can achieve competitive or superior performance.
RANK_REASON The item is a research paper detailing a new framework and experimental results for applying gradient-boosted trees in reinforcement learning. [lever_c_demoted from research: ic=1 ai=1.0]
- DeepCFR
- Flop5 Hold'em
- Goofspiel
- Kuhn's poker
- Leduc Hold'em
- Liar's Dice
- LightGBM
- Neural Networks
- Othello
- RL
- Tic-tac-toe
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
