Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Inverse Reinforcement Learning on MuJoCo halfcheetah (medium)
Loading...
12,174.61
Average Reward
Expert Performance
388.134
3,448.0845
6,508.035
9,567.9855
Feb 15, 2023
Average Reward
Updated 4d ago
Evaluation Results
Method
Method
Links
Average Reward
Expert Performance
expert demonstrations=...
2023.02
12,174.61
Offline ML-IRL
expert demonstrations=...
2023.02
7,640.73
BC
expert demonstrations=...
2023.02
4,471.72
ValueDICE
expert demonstrations=...
2023.02
1,125.17
CLARE
expert demonstrations=...
2023.02
841.46
Feedback
Search any
task
Search any
task