Our new X account is live! Follow @wizwand_team for updates

Unsupervised Reinforcement Learning on URL Benchmark (Walker)

237Flip Score

RND

Updated 4d ago

Evaluation Results

Method	Links
RND 2022.10		237	89	392	195
APT 2022.10		235	91	401	204
CIC 2022.10		218	79	356	174
Disagreement 2022.10		207	78	366	167
Proto 2022.10		171	72	322	162
MOSS 2022.10		166	58	295	112
SMM 2022.10		117	49	229	100
ICM 2022.10		78	32	170	60
AS-BOB 2022.10		35	22	132	28
APS 2022.10		35	27	162	30
AS-ALICE 2022.10		31	24	139	28
DIAYN 2022.10		22	18	107	20