Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Reinforcement Learning on Stochastic D4RL Walker2d Medium MuJoCo
Loading...
1,537.3
Mean Return
CODAC-N
1,104.14
1,216.595
1,329.05
1,441.505
Jul 12, 2021
Mean Return
CVaR (0.1)
Updated 4d ago
Evaluation Results
Method
Method
Links
Mean Return
CVaR (0.1)
CODAC-N
objective=risk-neutral
2021.07
1,537.3
1,158.8
CODAC-N
Objective=Risk-neutral
2021.07
1,537.3
1,158.8
CQL
2021.07
1,524.3
1,343.8
CQL
2021.07
1,524.3
1,343.8
ORAAC
2021.07
1,134.1
663
ORAAC
2021.07
1,134.1
663
CODAC-C
objective=CVaR
2021.07
1,120.8
902.3
CODAC-C
Objective=Risk-sensitive
2021.07
1,120.8
902.3
Feedback
Search any
task
Search any
task
