Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Inverse Reinforcement Learning on D4RL Hopper Medium-Replay v2
Loading...
2,417.83
Cumulative Reward
ValueDICE
780.6204
1,205.6652
1,630.71
2,055.7548
Feb 15, 2023
Cumulative Reward
Updated 4d ago
Evaluation Results
Method
Method
Links
Cumulative Reward
ValueDICE
Expert Demonstrations=...
2023.02
2,417.83
Offline ML-IRL
Expert Demonstrations=...
2023.02
2,395.03
CLARE
Expert Demonstrations=...
2023.02
2,369.79
BC
Expert Demonstrations=...
2023.02
843.59
Feedback
Search any
task
Search any
task