ResearchBenchmarksReinforcement Learning on MountainCar gravity=0.035Follow-210.6Policy ValueP4L-511.576-433.438-355.3-277.162May 14, 2025Evaluation ResultsMethodMethodLinksPolicy ValueP4LK=3K=32025.05-210.6P4LK=AutoK=Auto2025.05-263.1P4LK=5K=52025.05-295.1FQI2025.05-362.9P4LK=2K=22025.05-471.8P4LK=4K=42025.05-500ACPI2025.05-500VL2025.05-500