Multi-Objective Reinforcement Learning on Amsterdam transport planning environment benchmark leaderboard · SOTA2 Research

Multi-Objective Reinforcement Learning on Amsterdam transport planning environment

0.97Normalized HypervolumePCN

Evaluation Results

Method	Links
PCN2024.11		0.97	0.99	0.82	0.13
LCN-Mean2024.11		0.81	0.94	0.99	0.01
PCN2024.11		0.8	0.95	0.69	0.48
LCN2024.11		0.8	0.93	0.93	0.03
LCN-Redist.2024.11		0.79	0.92	0.86	0.06
LCN2024.11		0.67	0.7	0.88	0.37
LCN-Redist.2024.11		0.53	0.55	0.71	0.45
LCN2024.11		0.41	0.21	0.45	0.43
LCN-Mean2024.11		0.27	0.15	0.85	0.4
GPI-LS2024.11		0.22	0.85	0.54	0.64
PCN2024.11		0.17	0.75	0.42	0.58
GPI-LS2024.11		0.12	0.3	0.16	0.54
GPI-LS2024.11		0.06	0.92	0.47	0.62
GPI-LS2024.11		0	0.67	0.32	0.7
PCN2024.11		0	0.8	0.43	0.67
PCN2024.11		0	0.76	0.49	0.63
PCN2024.11		0	0.62	0.42	0.66
PCN2024.11		0	0.59	0.34	0.71
PCN2024.11		0	0.36	0.37	0.72
PCN2024.11		0	0.32	0.22	0.74
LCN2024.11		0	0.55	0.61	0.52
LCN2024.11		0	0.58	0.66	0.47
LCN2024.11		0	0.47	0.73	0.5
LCN2024.11		0	0.79	0.45	0.6
LCN2024.11		0	0.44	0.89	0.67
LCN2024.11		0	0.5	0.62	0.57
LCN-Redist.2024.11		0	0.46	0.36	0.61
LCN-Redist.2024.11		0	0.79	0.4	0.64
LCN-Redist.2024.11		0	0.86	0.43	0.62
LCN-Redist.2024.11		0	0.89	0.41	0.64
LCN-Redist.2024.11		0	0.9	0.34	0.69
LCN-Redist.2024.11		0	0.88	0.42	0.69
LCN-Redist.2024.11		0	0.92	0.38	0.71
LCN-Mean2024.11		0	0.21	0.9	0.4
LCN-Mean2024.11		0	0.17	0.54	0.56
LCN-Mean2024.11		0	0.12	0.47	0.54
LCN-Mean2024.11		0	0.11	0.83	0.5
LCN-Mean2024.11		0	0.12	0.39	0.6
LCN-Mean2024.11		0	0.22	0.9	0.65
LCN-Mean2024.11		0	0.36	0.82	0.58