Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Reinforcement Learning on D4RL Walker2d Medium
Loading...
87.7
Normalized Avg Return
MOBILE
15.004
33.877
52.75
71.623
Oct 30, 2023
Dec 31, 2023
Mar 2, 2024
May 4, 2024
Jul 5, 2024
Sep 5, 2024
Nov 7, 2024
Normalized Avg Return
Updated 4d ago
Evaluation Results
Method
Method
Links
Normalized Avg Return
MOBILE
Implementation=Origina...
2024.11
87.7
MOPO
Implementation=Origina...
2024.11
84.1
C-LAP
Implementation=Reproduced
2024.11
82.5
RGG+
planning seeds=15
2023.10
82
RGG
planning seeds=15
2023.10
81.7
MOBILE
Implementation=Reproduced
2024.11
81
Diffuser
2023.10
79.7
PLAS
Implementation=Reproduced
2024.11
79.4
TT
2023.10
79
IQL
2023.10
78.3
MOPO
Implementation=Reproduced
2024.11
78
MOREL
2023.10
77.8
BC
2023.10
75.3
DT
2023.10
74
CQL
2023.10
72.5
PLAS
Implementation=Origina...
2024.11
44.6
MBOP
2023.10
41
MOPO
2023.10
17.8
Feedback
Search any
task
Search any
task