Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-Objective Reinforcement Learning on Lunar Lander 4d
Loading...
1.24
Hypervolume (HV)
SPFT
0.3976
0.6163
0.835
1.0537
Aug 4, 2025
Sep 4, 2025
Oct 5, 2025
Nov 6, 2025
Dec 7, 2025
Jan 7, 2026
Feb 8, 2026
Hypervolume (HV)
Expected Utility (EU)
Sparsity (SP)
Compute Time (CT) (hours)
Environment Steps
Updated 2d ago
Evaluation Results
Method
Method
Links
Hypervolume (HV)
Expected Utility (EU)
Sparsity (SP)
Compute Time (CT) (hours)
Environment Steps
SPFT
2025.08
1.24
2.36
1.75
-
480,000
D3PO
2026.02
1.23
2.39
32
10
-
C-MORL
2026.02
1.12
2.35
104
20
-
C-MORL
2025.08
1.12
2.35
1.04
-
500,000
GPI-LS
2026.02
1.06
1.81
13
5
-
GPI-LS
2025.08
1.06
1.69
0.13
-
500,000
PCN
2026.02
0.78
1.44
3
7
-
Envelope
2025.08
0.43
-2.84
0.19
-
500,000
Feedback
Search any
task
Search any
task
