Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline-to-online Reinforcement Learning on D4RL Walker medium discretized
Loading...
15.9
Online Normalised Score
DRIFT
1.236
5.043
8.85
12.657
May 12, 2026
Online Normalised Score
Offline Normalised Score
Updated 21d ago
Evaluation Results
Method
Method
Links
Online Normalised Score
Offline Normalised Score
DRIFT
discretisation=k-means...
2026.05
15.9
1
IQL
discretisation=k-means...
2026.05
13
0.3
CQL
discretisation=k-means...
2026.05
12.6
2.5
DQN
discretisation=k-means...
2026.05
12.3
1.8
PEX
discretisation=k-means...
2026.05
11.8
0.3
Cal-QL
discretisation=k-means...
2026.05
11.7
2.5
PPO
discretisation=k-means...
2026.05
7.2
-
AWAC
discretisation=k-means...
2026.05
5.8
4.2
SPA
discretisation=k-means...
2026.05
1.8
1.8
Feedback
Search any
task
Search any
task
