Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline-to-online Reinforcement Learning on pen
Loading...
5.3
Regret
SMAC
3.304
16.777
30.25
43.723
Feb 19, 2026
Regret
Updated 4d ago
Evaluation Results
Method
Method
Links
Regret
SMAC
Offline Algorithm=SMAC...
2026.02
5.3
SMAC
Fine-tuning algorithm=...
2026.02
7.7
CalQL/CQL
Offline Algorithm=CalQ...
2026.02
8
IQL
Offline Algorithm=IQL,...
2026.02
10.3
SMAC
Offline Algorithm=SMAC...
2026.02
13.3
IQL
Fine-tuning algorithm=...
2026.02
16.1
CalQL/CQL
Fine-tuning algorithm=...
2026.02
17.8
IQL
Offline Algorithm=IQL,...
2026.02
18
CalQL/CQL
Offline Algorithm=CalQ...
2026.02
28.8
TD3+BC
Fine-tuning algorithm=...
2026.02
31.8
TD3+BC
Offline Algorithm=TD3+...
2026.02
32.9
TD3+BC
Offline Algorithm=TD3+...
2026.02
55.2
Feedback
Search any
task
Search any
task