Inverse Transition Learning on Randomworlds 40% stochastic-policy states benchmark leaderboard · SOTA2 Research

Inverse Transition Learning on Randomworlds 40% stochastic-policy states

76Epsilon MatchingITL

Evaluation Results

Method	Links
ITL2024.11		76	50	58	37	0.65	102.02	-404.02	-397.26	-366.43	0
BITL2024.11		75	38	57	26	5,561	123.3	-423.21	-398.25	-364.34	0
MCE2024.11		54	46	38	34	36.61	111.08	-522.35	-514.69	-459.71	11.81
MLE2024.11		43	46	29	34	0	111.07	-525.94	-519.63	-481.98	17.23
PS2024.11		30	31	19	20	2.61	127.02	-452.19	-444.69	-434.24	11.66