Share your thoughts, 1 month free Claude Pro on usSee more

Reinforcement Learning on CartPole v0

200Mean Score

CBRL

Updated 17d ago

Evaluation Results

Method	Links
CBRL 2024.06		200	0
CBRL 2024.06		200	0
CBRL 2024.06		200	0
CBRL 2024.06		200	0
CBRL 2024.06		200	0
CBRL 2024.06		200	0
CBRL 2024.06		200	0
CBRL 2024.06		200	0
CBRL 2024.06		199.69	0.63
XLVIN-R 2021.10		199.2	-
XLVIN-CP 2021.10		195.2	-
Linear 2024.06		187.7	23.72
PPO 2024.06		186.16	22.05
PPO 2024.06		183.12	10.49
PRAE, J = 5 2021.10		171.53	-
Linear 2024.06		165.75	45.35
CBRL 2024.06		163.49	30.57
LD-AE 2021.10		154.73	-
DQN 2024.06		154.46	24.42
PPO 2024.06		147.52	66.2
Linear 2024.06		138.79	57.88
PPO 2024.06		127.67	71.26
DQN 2024.06		123.49	20.59
Linear 2024.06		118.56	66.73
WM-AE 2021.10		114.47	-
Linear 2024.06		107.18	67.03
PPO 2021.10		104.6	-
PPO 2024.06		102.31	57.89
DQN 2024.06		80.85	31.94
Linear 2024.06		80.05	56.27
PPO 2024.06		75.65	50.67
DMDP-H (J = 0) 2021.10		72.81	-
PPO 2024.06		57.84	43.68
DQN 2024.06		56.44	31.43
PPO 2024.06		53.58	32.06
Linear 2024.06		50.77	26.93
PPO 2024.06		49.3	22.28
Linear 2024.06		37.2	14.8
DQN 2024.06		32.59	21.07
Linear 2024.06		27.15	7.79
Linear 2024.06		27.05	7.21
PPO 2024.06		26.19	15.18
REINFORCE 2021.10		23.84	-
DQN 2024.06		19.99	0.67
DQN 2024.06		19.76	1.08
DQN 2024.06		19.47	1.79
DQN 2024.06		18.88	3.35
DQN 2024.06		18.85	1.23