ResearchBenchmarksReinforcement Learning on MountainCar gravity=0.01Follow-44.79Policy ValueACPI-386.1284-297.5117-208.895-120.2783May 14, 2025Evaluation ResultsMethodMethodLinksPolicy ValueACPI2025.05-44.79P4LK=3K=32025.05-56.8P4LK=AutoK=Auto2025.05-63.2P4LK=5K=52025.05-67.6P4LK=4K=42025.05-74.23P4LK=2K=22025.05-106.3FQI2025.05-176.1VL2025.05-373