Order Completion on E-II environment mu = 0.75 benchmark leaderboard · SOTA2 Research

Order Completion on E-II environment mu = 0.75

71Overall Success RateIPPO

Evaluation Results

Method	Links
IPPO2026.07		71	100	89	62	60	58	57
Bischoff2026.07		65	91	79	57	55	53	52
Fixed 100,202026.07		65	93	81	56	54	54	53
Fixed 85,202026.07		62	90	77	55	52	49	47
Fixed 100,352026.07		61	91	77	54	51	48	46
Fixed 85,352026.07		58	86	76	48	45	47	46
CTDE PPO2026.07		51	70	62	45	43	42	42
DQN2026.07		46	79	7	53	47	48	43
High Low2026.07		41	56	52	39	37	31	30