{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3T472DAFTCENHW2DY6FXFTBC7L","short_pith_number":"pith:3T472DAF","schema_version":"1.0","canonical_sha256":"dcf9fd0c059888d3db43c78b72cc22fae31a4d6539d9f8951f8c4cffef39573d","source":{"kind":"arxiv","id":"1905.11222","version":2},"attestation_state":"computed","paper":{"title":"Soft Options Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Elita Lobo, Scott Jordan","submitted_at":"2019-05-23T21:27:11Z","abstract_excerpt":"The option-critic architecture (Bacon, Harb, and Precup 2017) and several variants have successfully demonstrated the use of the options framework proposed by Sutton et al (Sutton, Precup, and Singh1999) to scale learning and planning in hierarchical tasks. Although most of these frameworks use entropy as a regularizer to improve exploration, they do not maximize entropy along with returns at every time step. (Haarnoja et al., 2018d) recently introduced an off-policy actor critic algorithm in theSoft Actor Critic paper that maximize returns while maximizing entropy in a constrained manner thus"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.11222","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-05-23T21:27:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c399386b44dc73e6ccf9d5af935286c0bef01a91297f256b78f28d4add30d350","abstract_canon_sha256":"ab2fe89ebf172dd5698b29f44871bc616bf8ab21f65c59dc82f51250e64322fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:32.586077Z","signature_b64":"qRidKYAKZJ/khziLE2pfMgkANncfNnfr9TCcW2HqBy8bDGjfiXc9sVd3KhD1rWLWmjflepC9CxrHtyXucfF1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcf9fd0c059888d3db43c78b72cc22fae31a4d6539d9f8951f8c4cffef39573d","last_reissued_at":"2026-05-17T23:43:32.585675Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:32.585675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soft Options Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Elita Lobo, Scott Jordan","submitted_at":"2019-05-23T21:27:11Z","abstract_excerpt":"The option-critic architecture (Bacon, Harb, and Precup 2017) and several variants have successfully demonstrated the use of the options framework proposed by Sutton et al (Sutton, Precup, and Singh1999) to scale learning and planning in hierarchical tasks. Although most of these frameworks use entropy as a regularizer to improve exploration, they do not maximize entropy along with returns at every time step. (Haarnoja et al., 2018d) recently introduced an off-policy actor critic algorithm in theSoft Actor Critic paper that maximize returns while maximizing entropy in a constrained manner thus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11222","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.11222","created_at":"2026-05-17T23:43:32.585760+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11222v2","created_at":"2026-05-17T23:43:32.585760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11222","created_at":"2026-05-17T23:43:32.585760+00:00"},{"alias_kind":"pith_short_12","alias_value":"3T472DAFTCEN","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"3T472DAFTCENHW2D","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"3T472DAF","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L","json":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L.json","graph_json":"https://pith.science/api/pith-number/3T472DAFTCENHW2DY6FXFTBC7L/graph.json","events_json":"https://pith.science/api/pith-number/3T472DAFTCENHW2DY6FXFTBC7L/events.json","paper":"https://pith.science/paper/3T472DAF"},"agent_actions":{"view_html":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L","download_json":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L.json","view_paper":"https://pith.science/paper/3T472DAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11222&json=true","fetch_graph":"https://pith.science/api/pith-number/3T472DAFTCENHW2DY6FXFTBC7L/graph.json","fetch_events":"https://pith.science/api/pith-number/3T472DAFTCENHW2DY6FXFTBC7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L/action/storage_attestation","attest_author":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L/action/author_attestation","sign_citation":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L/action/citation_signature","submit_replication":"https://pith.science/pith/3T472DAFTCENHW2DY6FXFTBC7L/action/replication_record"}},"created_at":"2026-05-17T23:43:32.585760+00:00","updated_at":"2026-05-17T23:43:32.585760+00:00"}