Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline-to-online Reinforcement Learning on D4RL Cheetah medium discretized
Loading...
16.9
Online Score
DQN
1.508
5.504
9.5
13.496
May 12, 2026
Online Score
Offline Score
Updated 21d ago
Evaluation Results
Method
Method
Links
Online Score
Offline Score
DQN
discretisation=k-means...
2026.05
16.9
2.1
CQL
discretisation=k-means...
2026.05
15.8
3.3
Cal-QL
discretisation=k-means...
2026.05
15.8
3.3
PEX
discretisation=k-means...
2026.05
14.6
0.2
AWAC
discretisation=k-means...
2026.05
12.7
13.1
DRIFT
discretisation=k-means...
2026.05
11.1
0.2
IQL
discretisation=k-means...
2026.05
7.8
0.2
PPO
discretisation=k-means...
2026.05
4.9
-
SPA
discretisation=k-means...
2026.05
2.1
2.1
Feedback
Search any
task
Search any
task