Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Inverse Reinforcement Learning on D4RL HalfCheetah Medium v2
Loading...
9,313.29
Cumulative Reward
Offline ML-IRL
-555.4364
2,006.6368
4,568.71
7,130.7832
Feb 15, 2023
Cumulative Reward
Updated 4d ago
Evaluation Results
Method
Method
Links
Cumulative Reward
Offline ML-IRL
Expert Demonstrations=...
2023.02
9,313.29
Offline ML-IRL
Expert Demonstrations=...
2023.02
7,690.3
BC
Expert Demonstrations=...
2023.02
2,799.4
BC
Expert Demonstrations=...
2023.02
2,799.4
CLARE
Expert Demonstrations=...
2023.02
343.37
CLARE
Expert Demonstrations=...
2023.02
240.5
ValueDICE
Expert Demonstrations=...
2023.02
-175.87
ValueDICE
Expert Demonstrations=...
2023.02
-175.87
Feedback
Search any
task
Search any
task