Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Objective Reinforcement Learning on Deep Sea Treasure
Loading...
22,845.4
Hypervolume (HV)
PCN
-907.9608
5,258.7771
11,425.515
17,592.2529
Nov 27, 2024
Feb 21, 2025
May 18, 2025
Aug 12, 2025
Nov 6, 2025
Jan 31, 2026
Apr 27, 2026
Hypervolume (HV)
Expected Utility Metric (EUM)
UT Score
ED Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Hypervolume (HV)
Expected Utility Metric (EUM)
UT Score
ED Score
PCN
2024.11
22,845.4
53.82
-
-
LCN
2024.11
22,838
53.76
-
-
GPI-LS
2024.11
22,622.8
53.86
-
-
MORL-FB
2026.04
9.92
-
6.43
-
Optimal
2026.04
9.92
-
6.89
-
Envelope
2026.04
9.91
-
6.53
77
PD-MORL
interpolator=with
2026.04
9.33
-
0.52
69
PCN
2026.04
8.71
-
6.12
81
SFOLS
2026.04
8.46
-
5.65
25
MORL/D
2026.04
5.63
-
3.88
15
Feedback
Search any
task
Search any
task