Safe Reinforcement Learning on 2D Quadrotor Fixed Obstacles benchmark leaderboard · SOTA2 Research

Safe Reinforcement Learning on 2D Quadrotor Fixed Obstacles

100Verified Count (50)VSRL

Evaluation Results

Method	Links
VSRL2024.05		100	50	100	100	40,120
RESPO2024.05		60.4	14	99.9	99.9	33,919
MBPPO2024.05		58.9	9	99.9	84.5	39,911
PPO-Lag2024.05		0	5	83.4	83.4	40,530
PPO-PID2024.05		0	4	99.3	97.5	41,125
CAP2024.05		0	3	99.5	99.5	39,312
CBF-RL2024.05		0	5	89.9	89.7	40,817