Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Inverse Reinforcement Learning on MuJoCo halfcheetah (medium-replay)
Loading...
12,174.61
Average Reward
Expert Performance
-32.3172
3,136.7889
6,305.895
9,475.0011
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
9,236.84
BC
expert demonstrations=...
2023.02
4,471.72
ValueDICE
expert demonstrations=...
2023.02
1,125.17
CLARE
expert demonstrations=...
2023.02
437.18
Feedback
Search any
task
Search any
task