ResearchBenchmarksReinforcement Learning on CartPole Setting A v0 (test)Reinforcement Learning on CartPole Setting A v0 (test)Follow98.2Performance Score (Config 2/0.85)P4L30.0847.76565.4583.135May 14, 2025Evaluation resultsMethodMethodLinksPerformance Score (Config 2/0.85)Performance Score (Config 5/0.85)Performance Score (Config 10/0.85)P4LK=AutoK=Auto2025.0598.2174.2213P4LK=3K=32025.0592.4182.8226ACPI2025.0589.4168.2200.1P4LK=5K=52025.0586.2163.2192.8P4LK=4K=42025.0574.3179.6165.5FQI2025.0563.465.9100.2P4LK=2K=22025.055872.8121.1VL2025.0532.771.595.1