ResearchBenchmarksPitch Control on Quanser Aero 2 Gymnasium (simulation)Follow0.0246Pitch Deviation (rad)CH-3-PPO0.0111480.1019490.192750.283551May 21, 2026Evaluation ResultsMethodMethodLinksPitch Deviation (rad)R Cost/PenaltyAction Magnitude (V)Power Consumption (W)CH-3-PPOevaluation episodes=10evaluation episodes=102026.050.024649.24.43381.6545PPOevaluation episodes=10evaluation episodes=102026.050.042384.616.362337.0509CH-3-ARSevaluation episodes=10evaluation episodes=102026.050.0626125.24.08281.3331ARSevaluation episodes=10evaluation episodes=102026.050.3609721.80.93050.0559