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

Reinforcement Learning Control on Pendulum v1

1,378.78Mean Score

CBRL

90.0848424.6499759.2151,093.7801Jun 20, 2024
Updated 2mo ago

Evaluation Results

MethodLinks
2024.06
1,378.7843.89
2024.06
1,331.7336.25
2024.06
1,147.35181.2
2024.06
1,145.353.57
2024.06
1,088.6783.73
2024.06
1,062.06102.63
2024.06
1,058.8892.55
2024.06
1,057.0290.29
2024.06
1,044.34100.9
2024.06
1,036.6588.37
2024.06
1,032.8287.11
2024.06
1,004.75101.66
2024.06
999.4178.75
2024.06
942.18170.83
2024.06
757.11205.66
2024.06
561.78384.15
2024.06
559.65151.39
2024.06
524.1259.46
2024.06
511.85181.28
2024.06
385.5365.39
2024.06
355.09324.16
2024.06
325.66133.77
2024.06
296.94184.32
2024.06
284.26130.17
2024.06
241.16162.85
2024.06
240.94149.57
2024.06
222.83146.68
2024.06
222.18151.71
2024.06
221.78150.4
2024.06
220.5148.68
2024.06
220.38148.54
2024.06
220.28148.8
2024.06
218.37100.83
2024.06
172.4848.32
2024.06
152.837.43
2024.06
149.3451.7
2024.06
145.5644.16
2024.06
143.9540.91
2024.06
141.836.63
2024.06
139.6532.36