Multi-Objective Reinforcement Learning on Queue benchmark leaderboard · SOTA2 Research

Multi-Objective Reinforcement Learning on Queue

1.6MERHEURISTIC

Evaluation Results

Method	Links
HEURISTIC2026.03		1.6	10.05
ENVELOPE2026.03		3.54	25.1
DPI2026.03		3.74	29.09
FIXED2026.03		4.19	10.05
RS2026.03		4.29	11.43
SR-PPO2026.03		5.64	46.91
DPI2026.03		10.34	39.95
DPI-PPO2026.03		10.34	39.95
Dense Oracle2026.03		14.41	49.27
MER-PPO2026.03		15.01	0.98
RANDOM2026.03		24.24	17.25