Reinforcement Learning Control on Pendulum v1 benchmark leaderboard · SOTA2 Research

Reinforcement Learning Control on Pendulum v1

1,378.78Mean ScoreCBRL

Evaluation Results

Method	Links
CBRL2024.06		1,378.78	43.89
Linear2024.06		1,331.73	36.25
PPO2024.06		1,147.35	181.2
Linear2024.06		1,145.3	53.57
Linear2024.06		1,088.67	83.73
Linear2024.06		1,062.06	102.63
Linear2024.06		1,058.88	92.55
Linear2024.06		1,057.02	90.29
Linear2024.06		1,044.34	100.9
Linear2024.06		1,036.65	88.37
Linear2024.06		1,032.82	87.11
CBRL2024.06		1,004.75	101.66
Linear2024.06		999.41	78.75
DDPG2024.06		942.18	170.83
PPO2024.06		757.11	205.66
PPO2024.06		561.78	384.15
PPO2024.06		559.65	151.39
PPO2024.06		524.1	259.46
PPO2024.06		511.85	181.28
PPO2024.06		385.5	365.39
DDPG2024.06		355.09	324.16
PPO2024.06		325.66	133.77
PPO2024.06		296.94	184.32
CBRL2024.06		284.26	130.17
DDPG2024.06		241.16	162.85
DDPG2024.06		240.94	149.57
DDPG2024.06		222.83	146.68
DDPG2024.06		222.18	151.71
DDPG2024.06		221.78	150.4
DDPG2024.06		220.5	148.68
DDPG2024.06		220.38	148.54
DDPG2024.06		220.28	148.8
PPO2024.06		218.37	100.83
CBRL2024.06		172.48	48.32
CBRL2024.06		152.8	37.43
CBRL2024.06		149.34	51.7
CBRL2024.06		145.56	44.16
CBRL2024.06		143.95	40.91
CBRL2024.06		141.8	36.63
CBRL2024.06		139.65	32.36