ResearchBenchmarksSafe Reinforcement Learning on 2D Quadrotor Fixed ObstaclesSafe Reinforcement Learning on 2D Quadrotor Fixed ObstaclesFollow100Verified Count (50)VSRL-4235077May 25, 2024Evaluation resultsMethodMethodLinksVerified Count (50)Verified MaxEmpirical Score (50)Empirical Score (500)Average RewardVSRL2024.051005010010040,120RESPO2024.0560.41499.999.933,919MBPPO2024.0558.9999.984.539,911PPO-Lag2024.050583.483.440,530PPO-PID2024.050499.397.541,125CAP2024.050399.599.539,312CBF-RL2024.050589.989.740,817