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

Offline Reinforcement Learning on D4RL mujoco-hopper (med-replay)

100Normalized Score

DD

-2.75223.92450.677.276Oct 1, 2021Feb 4, 2022Jun 11, 2022Oct 16, 2022Feb 19, 2023Jun 26, 2023Oct 31, 2023
Updated 3mo ago

Evaluation Results

MethodLinks
2023.10
100
2021.10
98.1
2023.10
97.8
2021.10
97
2023.10
95
2023.10
94.7
2021.10
93.6
2023.10
91.5
2023.10
87.6
2023.10
83.4
2023.10
82.7
2023.10
75.9
2021.10
73.1
2023.10
60.9
2021.10
54.7
2021.10
53.2
2021.10
39.1
2021.10
39.1
2021.10
30.6
2021.10
8.1
2021.10
6.1
2021.10
5.7
2021.10
1.2