{"id":"oscr:b:5N5QZYT5GFMHS-I","url":"https://openscicode.org/b/oscr:b:5N5QZYT5GFMHS-I","status":"current","doi":"10.1186/s13040-026-00571-z","since":"2026-11-14","page":"doi_10.1186_s13040-026-00571-z","repo":"github.com/tenglong322/dag-vaerl","commit":"533ee14130b88ec3f707e7cb379c0e5653b5d8c4","path":"rl_training.py","swhid":"swh:1:cnt:95df219bb9cd223a98989bfef0cb8139c457ca03","lines":[14,95],"symbol":"train_rl_epoch","paragraphs":[[41,"Method › Reinforcement learning formulation and policy network › Training and op"]],"method":"lexical-v1","origin":"machine","paper":"https://doi.org/10.1186/s13040-026-00571-z","swhid_qualified":"swh:1:cnt:95df219bb9cd223a98989bfef0cb8139c457ca03;origin=https://github.com/tenglong322/dag-vaerl;anchor=swh:1:rev:533ee14130b88ec3f707e7cb379c0e5653b5d8c4;path=/rl_training.py;lines=14-95","reader":"https://openscicode.org/paper/doi_10.1186_s13040-026-00571-z/?path=rl_training.py#L14-L95","citation":"Code block oscr:b:5N5QZYT5GFMHS-I (https://openscicode.org/b/oscr:b:5N5QZYT5GFMHS-I)\nrl_training.py, lines 14 to 95, in github.com/tenglong322/dag-vaerl (https://github.com/tenglong322/dag-vaerl), commit 533ee14130b88ec3f707e7cb379c0e5653b5d8c4.\nPaper: https://doi.org/10.1186/s13040-026-00571-z\nSWHID: swh:1:cnt:95df219bb9cd223a98989bfef0cb8139c457ca03;origin=https://github.com/tenglong322/dag-vaerl;anchor=swh:1:rev:533ee14130b88ec3f707e7cb379c0e5653b5d8c4;path=/rl_training.py;lines=14-95"}