Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline-to-online Reinforcement Learning on D4RL Cheetah expert discretized
Loading...
9.7
Online Normalized Score
DRIFT
-0.284
2.308
4.9
7.492
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
9.7
0.5
CQL
discretisation=k-means...
2026.05
8.6
0.7
Cal-QL
discretisation=k-means...
2026.05
8.5
0.7
PEX
discretisation=k-means...
2026.05
7.7
0.2
IQL
discretisation=k-means...
2026.05
6.8
0.2
PPO
discretisation=k-means...
2026.05
5.9
-
DQN
discretisation=k-means...
2026.05
4.7
0.1
AWAC
discretisation=k-means...
2026.05
1
1.1
SPA
discretisation=k-means...
2026.05
0.1
0.1
Feedback
Search any
task
Search any
task