Safe Reinforcement Learning on 3D Quadrotor Fixed Obstacles benchmark leaderboard · SOTA2 Research

Safe Reinforcement Learning on 3D Quadrotor Fixed Obstacles

100Verified-15 CountVSRL

Evaluation Results

Method	Links
VSRL2024.05		100	15	100	100	12,214
MBPPO2024.05		41.1	1	75.4	73.1	1,329
PPO-Lag2024.05		0	3	85.2	81.2	13,211
PPO-PID2024.05		0	3	89.4	88.3	14,512
CAP2024.05		0	4	63.6	59.2	14,111
CBF-RL2024.05		0	2	82.3	79.2	14,010
RESPO2024.05		0	1	65.7	21.3	798