Jacob Hilton et al.: Batch size-invariance for policy optimization. (2021)journals/corr/abs-2110-006412110.00641Batch size-invariance for policy optimization.3Jacob Hilton1Karl Cobbe2John Schulman3CoRRCoRRabs/2110.006412021provenance information for RDF data of dblp record 'journals/corr/abs-2110-00641'2021-10-08T15:47:55+0200