ResearchBenchmarksReinforcement Learning on CartPole Setting B v0 (test)Reinforcement Learning on CartPole Setting B v0 (test)Follow192.4Steps Survived (Config 0.15)P4L118.56137.73156.9176.07May 14, 2025Evaluation resultsMethodMethodLinksSteps Survived (Config 0.15)Steps Survived (Config 0.5)Steps Survived (Config 0.85)P4LK=3K=32025.05192.4204.6164P4LK=AutoK=Auto2025.05174.2206154.8P4LK=4K=42025.05170.3211.6157.5ACPI2025.05168.4216.4151.1P4LK=5K=52025.05166.2197.2152.8P4LK=2K=22025.05161142.898.1VL2025.05146.7181.5110.1FQI2025.05121.4154.9122