Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Reinforcement Learning on Stochastic D4RL Cheetah MuJoCo (Medium)
Loading...
361.4
Mean Return
ORAAC
20.072
108.686
197.3
285.914
Jul 12, 2021
Mean Return
CVaR 0.1
Updated 4d ago
Evaluation Results
Method
Method
Links
Mean Return
CVaR 0.1
ORAAC
2021.07
361.4
91.3
ORAAC
2021.07
361.4
91.3
CODAC-N
objective=risk-neutral
2021.07
338
-41
CODAC-N
Objective=Risk-neutral
2021.07
338
-41
CODAC-C
objective=CVaR
2021.07
335
-27
CODAC-C
Objective=Risk-sensitive
2021.07
335
-27
CQL
2021.07
33.2
-15
CQL
2021.07
33.2
-15
Feedback
Search any
task
Search any
task