{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7MR74TPLEPHHSVQIBLHXHZL56A","short_pith_number":"pith:7MR74TPL","schema_version":"1.0","canonical_sha256":"fb23fe4deb23ce7956080acf73e57df03bcc78025047922abb2315288ab091d7","source":{"kind":"arxiv","id":"1901.01365","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Masashi Sugiyama, Takayuki Osa, Voot Tangkaratt","submitted_at":"2019-01-05T04:43:05Z","abstract_excerpt":"Real-world tasks are often highly structured. Hierarchical reinforcement learning (HRL) has attracted research interest as an approach for leveraging the hierarchical structure of a given task in reinforcement learning (RL). However, identifying the hierarchical policy structure that enhances the performance of RL is not a trivial task. In this paper, we propose an HRL method that learns a latent variable of a hierarchical policy using mutual information maximization. Our approach can be interpreted as a way to learn a discrete and latent representation of the state-action space. To learn opti"},"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":"1901.01365","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-05T04:43:05Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4df7b9843c8a1b5c70f5338dfbc3a1516843feac3413b4111087c25a6f1353eb","abstract_canon_sha256":"d2a59d0b786990b3d68cb84c3b531c9549f242d112943bf89728e779cb1e154d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:52.134570Z","signature_b64":"uC2ZhPtMEezq4QdHwS8BLf+rI7i7EoWYUKFMdfRlDzOLkgHNuXJJ4yCT6VpwZxshZaBnGWF6RVvJK0aycYJfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb23fe4deb23ce7956080acf73e57df03bcc78025047922abb2315288ab091d7","last_reissued_at":"2026-05-17T23:51:52.133910Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:52.133910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Masashi Sugiyama, Takayuki Osa, Voot Tangkaratt","submitted_at":"2019-01-05T04:43:05Z","abstract_excerpt":"Real-world tasks are often highly structured. Hierarchical reinforcement learning (HRL) has attracted research interest as an approach for leveraging the hierarchical structure of a given task in reinforcement learning (RL). However, identifying the hierarchical policy structure that enhances the performance of RL is not a trivial task. In this paper, we propose an HRL method that learns a latent variable of a hierarchical policy using mutual information maximization. Our approach can be interpreted as a way to learn a discrete and latent representation of the state-action space. To learn opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01365","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":"1901.01365","created_at":"2026-05-17T23:51:52.133987+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.01365v2","created_at":"2026-05-17T23:51:52.133987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01365","created_at":"2026-05-17T23:51:52.133987+00:00"},{"alias_kind":"pith_short_12","alias_value":"7MR74TPLEPHH","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7MR74TPLEPHHSVQI","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7MR74TPL","created_at":"2026-05-18T12:33:12.712433+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/7MR74TPLEPHHSVQIBLHXHZL56A","json":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A.json","graph_json":"https://pith.science/api/pith-number/7MR74TPLEPHHSVQIBLHXHZL56A/graph.json","events_json":"https://pith.science/api/pith-number/7MR74TPLEPHHSVQIBLHXHZL56A/events.json","paper":"https://pith.science/paper/7MR74TPL"},"agent_actions":{"view_html":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A","download_json":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A.json","view_paper":"https://pith.science/paper/7MR74TPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.01365&json=true","fetch_graph":"https://pith.science/api/pith-number/7MR74TPLEPHHSVQIBLHXHZL56A/graph.json","fetch_events":"https://pith.science/api/pith-number/7MR74TPLEPHHSVQIBLHXHZL56A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A/action/storage_attestation","attest_author":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A/action/author_attestation","sign_citation":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A/action/citation_signature","submit_replication":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A/action/replication_record"}},"created_at":"2026-05-17T23:51:52.133987+00:00","updated_at":"2026-05-17T23:51:52.133987+00:00"}