ResearchBenchmarksReinforcement Learning on MountainCar (Return Mean and Std)Reinforcement Learning on MountainCar (Return Mean and Std)Follow-41.98Return (Selected)FPSRL-43.5296-43.1273-42.725-42.3227Oct 19, 2016Evaluation resultsMethodMethodLinksReturn (Selected)Return (Mean)Return (Std)FPSRLBatch size=1,000Batch size=1,0002016.10-41.98-41.990.01FPSRLBatch size=100,000Batch size=100,0002016.10-41.99-41.930.11FPSRLBatch size=10,000Batch size=10,0002016.10-42.22-42.690.46NFQBatch size=100,000Batch size=100,0002016.10-43.12-43.281.22NFQBatch size=1,000Batch size=1,0002016.10-43.23-44.871.33NFQBatch size=10,000Batch size=10,0002016.10-43.47-45.732.9