Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Offline-to-online Reinforcement Learning on door
Loading...
50.3
Regret
SMAC
46.68
71.115
95.55
119.985
Feb 19, 2026
Regret
Updated 1mo ago
Evaluation Results
Method
Method
Links
Regret
SMAC
Offline Algorithm=SMAC...
2026.02
50.3
SMAC
Fine-tuning algorithm=...
2026.02
72.3
IQL
Offline Algorithm=IQL,...
2026.02
120
SMAC
Offline Algorithm=SMAC...
2026.02
122.8
IQL
Fine-tuning algorithm=...
2026.02
127
IQL
Offline Algorithm=IQL,...
2026.02
127.9
TD3+BC
Offline Algorithm=TD3+...
2026.02
129.7
CalQL/CQL
Offline Algorithm=CalQ...
2026.02
129.9
CalQL/CQL
Offline Algorithm=CalQ...
2026.02
134.5
TD3+BC
Offline Algorithm=TD3+...
2026.02
136
TD3+BC
Fine-tuning algorithm=...
2026.02
140.3
CalQL/CQL
Fine-tuning algorithm=...
2026.02
140.8
Feedback
Search any
task
Search any
task
