Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline-to-online Reinforcement Learning on D4RL Walker expert discretized
Loading...
14.8
Online Normalized Score
DRIFT
-0.384
3.558
7.5
11.442
May 12, 2026
Online Normalized Score
Offline Normalized Score
Updated 21d ago
Evaluation Results
Method
Method
Links
Online Normalized Score
Offline Normalized Score
DRIFT
discretisation=k-means...
2026.05
14.8
0.1
Cal-QL
discretisation=k-means...
2026.05
12.4
4
CQL
discretisation=k-means...
2026.05
10.7
4
IQL
discretisation=k-means...
2026.05
10.1
0.2
AWAC
discretisation=k-means...
2026.05
9
9.4
PEX
discretisation=k-means...
2026.05
7.2
0.2
PPO
discretisation=k-means...
2026.05
7
-
DQN
discretisation=k-means...
2026.05
6.5
0.2
SPA
discretisation=k-means...
2026.05
0.2
0.2
Feedback
Search any
task
Search any
task
