Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Offline Reinforcement Learning on Stochastic D4RL Hopper MuJoCo (Mixed)
Loading...
1,551.2
Mean Return
CODAC-C
134.72
502.46
870.2
1,237.94
Jul 12, 2021
Mean Return
CVaR 0.1 Return
Updated 4d ago
Evaluation Results
Method
Method
Links
Mean Return
CVaR 0.1 Return
CODAC-C
objective=CVaR
2021.07
1,551.2
1,449.6
CODAC-C
Objective=Risk-sensitive
2021.07
1,551.2
1,449.6
CODAC-N
objective=risk-neutral
2021.07
1,483.9
1,457.6
CODAC-N
Objective=Risk-neutral
2021.07
1,483.9
1,457.6
ORAAC
2021.07
876.3
524.9
ORAAC
2021.07
876.3
524.9
CQL
2021.07
189.2
-21.4
CQL
2021.07
189.2
-21.4
Feedback
Search any
task
Search any
task
