Reinforcement Learning on Lunar Lander POMDP benchmark leaderboard · SOTA2 Research

Reinforcement Learning on Lunar Lander POMDP

56.09Performance ScoreVOMCPOW

Evaluation Results

Method	Links
VOMCPOW2025.03		56.09	0.081
POMCPOW2025.03		54.89	0.136
VOMCPOW2025.03		53.67	0.144
POMCPOW2025.03		52.67	0.075
AG-PFT-VPW2025.03		52	0.508
AG-PFT-DPW2025.03		51.69	0.184
POMCPOW2025.03		51.65	0.037
AG-PFT-DPW2025.03		51.47	0.504
VOMCPOW2025.03		49.52	0.037
AG-PFT-VPW2025.03		47.34	0.186
PFT-DPW2025.03		46.23	0.053
POMCPOW2025.03		45.5	0.025
AG-PFT-DPW2025.03		45.49	0.081
PFT-DPW2025.03		44.72	0.103
AG-PFT-VPW2025.03		44.51	0.078
VOMCPOW2025.03		44.35	0.028
PFT-VPW2025.03		44.05	0.102
POMCPOW2025.03		42.13	0.088
VOMCPOW2025.03		41.96	0.145
PFT-VPW2025.03		41.27	0.053
PFT-VPW2025.03		41.24	0.031
AG-PFT-DPW2025.03		39.39	0.043
AG-PFT-VPW2025.03		37.07	0.041
PFT-DPW2025.03		36.11	0.031
PFT-VPW2025.03		30.36	0.019
PFT-DPW2025.03		25.03	0.018
AG-PFT-VPW2025.03		22.11	0.343
PFT-DPW2025.03		21.99	0.015
AG-PFT-DPW2025.03		20.93	0.307
PFT-VPW2025.03		12.59	0.02