{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FSYGATB3HGNHF3Y4Y44WUY4H5D","short_pith_number":"pith:FSYGATB3","schema_version":"1.0","canonical_sha256":"2cb0604c3b399a72ef1cc7396a6387e8e139c67aa8f76a8abec50d9512d9d9fe","source":{"kind":"arxiv","id":"2006.14363","version":1},"attestation_state":"computed","paper":{"title":"SOAC: The Soft Option Actor-Critic Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chenghao Li, Chongjie Zhang, Jun Yang, Li Xia, Qianchuan Zhao, Xiaoteng Ma","submitted_at":"2020-06-25T13:06:59Z","abstract_excerpt":"The option framework has shown great promise by automatically extracting temporally-extended sub-tasks from a long-horizon task. Methods have been proposed for concurrently learning low-level intra-option policies and high-level option selection policy. However, existing methods typically suffer from two major challenges: ineffective exploration and unstable updates. In this paper, we present a novel and stable off-policy approach that builds on the maximum entropy model to address these challenges. Our approach introduces an information-theoretical intrinsic reward for encouraging the identif"},"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":"2006.14363","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-25T13:06:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9f938a4ab24ee1c5368e12aa3503ac3fab3e665bb28e443a39f681f8148e91a8","abstract_canon_sha256":"4b65df263aca331d5c5add36eb2dba12d6aae102141968cc5c701b70b7fc2efd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:31.776096Z","signature_b64":"VNwfJKlh3Hp7hOQxsvGtnMsey+Pe2Rz0Sw0isZa1KaXpspQ4CvIZjcGKGPuMcHPTwTDxpN33FqsOjXxKH0vjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cb0604c3b399a72ef1cc7396a6387e8e139c67aa8f76a8abec50d9512d9d9fe","last_reissued_at":"2026-07-05T01:13:31.775602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:31.775602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOAC: The Soft Option Actor-Critic Architecture","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Chenghao Li, Chongjie Zhang, Jun Yang, Li Xia, Qianchuan Zhao, Xiaoteng Ma","submitted_at":"2020-06-25T13:06:59Z","abstract_excerpt":"The option framework has shown great promise by automatically extracting temporally-extended sub-tasks from a long-horizon task. Methods have been proposed for concurrently learning low-level intra-option policies and high-level option selection policy. However, existing methods typically suffer from two major challenges: ineffective exploration and unstable updates. In this paper, we present a novel and stable off-policy approach that builds on the maximum entropy model to address these challenges. Our approach introduces an information-theoretical intrinsic reward for encouraging the identif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14363","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.14363/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2006.14363","created_at":"2026-07-05T01:13:31.775663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.14363v1","created_at":"2026-07-05T01:13:31.775663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14363","created_at":"2026-07-05T01:13:31.775663+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSYGATB3HGNH","created_at":"2026-07-05T01:13:31.775663+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSYGATB3HGNHF3Y4","created_at":"2026-07-05T01:13:31.775663+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSYGATB3","created_at":"2026-07-05T01:13:31.775663+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FSYGATB3HGNHF3Y4Y44WUY4H5D","json":"https://pith.science/pith/FSYGATB3HGNHF3Y4Y44WUY4H5D.json","graph_json":"https://pith.science/api/pith-number/FSYGATB3HGNHF3Y4Y44WUY4H5D/graph.json","events_json":"https://pith.science/api/pith-number/FSYGATB3HGNHF3Y4Y44WUY4H5D/events.json","paper":"https://pith.science/paper/FSYGATB3"},"agent_actions":{"view_html":"https://pith.science/pith/FSYGATB3HGNHF3Y4Y44WUY4H5D","download_json":"https://pith.science/pith/FSYGATB3HGNHF3Y4Y44WUY4H5D.json","view_paper":"https://pith.science/paper/FSYGATB3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.14363&json=true","fetch_graph":"https://pith.science/api/pith-number/FSYGATB3HGNHF3Y4Y44WUY4H5D/graph.json","fetch_events":"https://pith.science/api/pith-number/FSYGATB3HGNHF3Y4Y44WUY4H5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSYGATB3HGNHF3Y4Y44WUY4H5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSYGATB3HGNHF3Y4Y44WUY4H5D/action/storage_attestation","attest_author":"https://pith.science/pith/FSYGATB3HGNHF3Y4Y44WUY4H5D/action/author_attestation","sign_citation":"https://pith.science/pith/FSYGATB3HGNHF3Y4Y44WUY4H5D/action/citation_signature","submit_replication":"https://pith.science/pith/FSYGATB3HGNHF3Y4Y44WUY4H5D/action/replication_record"}},"created_at":"2026-07-05T01:13:31.775663+00:00","updated_at":"2026-07-05T01:13:31.775663+00:00"}