Unsupervised Reinforcement Learning on URL Benchmark (Walker) benchmark leaderboard · SOTA2 Research

Unsupervised Reinforcement Learning on URL Benchmark (Walker)

237Flip ScoreRND

Evaluation Results

Method	Links
RND2022.10		237	89	392	195
APT2022.10		235	91	401	204
CIC2022.10		218	79	356	174
Disagreement2022.10		207	78	366	167
Proto2022.10		171	72	322	162
MOSS2022.10		166	58	295	112
SMM2022.10		117	49	229	100
ICM2022.10		78	32	170	60
AS-BOB2022.10		35	22	132	28
APS2022.10		35	27	162	30
AS-ALICE2022.10		31	24	139	28
DIAYN2022.10		22	18	107	20