{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DIS7JSXN2KNQMC2QTAHS63MDAK","short_pith_number":"pith:DIS7JSXN","schema_version":"1.0","canonical_sha256":"1a25f4caedd29b060b50980f2f6d8302bef75474c43009ca7cc42b32a0959470","source":{"kind":"arxiv","id":"1812.01487","version":2},"attestation_state":"computed","paper":{"title":"Hyperbolic Embeddings for Learning Options in Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"M. Prannoy, Saket Tiwari","submitted_at":"2018-12-04T15:30:23Z","abstract_excerpt":"Hierarchical reinforcement learning deals with the problem of breaking down large tasks into meaningful sub-tasks. Autonomous discovery of these sub-tasks has remained a challenging problem. We propose a novel method of learning sub-tasks by combining paradigms of routing in computer networks and graph based skill discovery within the options framework to define meaningful sub-goals. We apply the recent advancements of learning embeddings using Riemannian optimisation in the hyperbolic space to embed the state set into the hyperbolic space and create a model of the environment. In doing so we "},"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":"1812.01487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-04T15:30:23Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"26a3d0deeed1a157f93ae79bc3a031bb6dd978f86e4bf0f430fbd02c4aad4f83","abstract_canon_sha256":"6521c736e7d25b2150b5cd79ba36e5c5c13d324d0bc4f61dc3c541c7e80d2815"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:49.966484Z","signature_b64":"R6742h+5wx35vW4e83zYXLG8rsW0iDWQ6sHM7YUWmOvrDlAwSuJbbZeD/A0gGPLRreGAMWEySv8h6z4n+o4BDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a25f4caedd29b060b50980f2f6d8302bef75474c43009ca7cc42b32a0959470","last_reissued_at":"2026-05-17T23:53:49.965848Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:49.965848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperbolic Embeddings for Learning Options in Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"M. Prannoy, Saket Tiwari","submitted_at":"2018-12-04T15:30:23Z","abstract_excerpt":"Hierarchical reinforcement learning deals with the problem of breaking down large tasks into meaningful sub-tasks. Autonomous discovery of these sub-tasks has remained a challenging problem. We propose a novel method of learning sub-tasks by combining paradigms of routing in computer networks and graph based skill discovery within the options framework to define meaningful sub-goals. We apply the recent advancements of learning embeddings using Riemannian optimisation in the hyperbolic space to embed the state set into the hyperbolic space and create a model of the environment. In doing so we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01487","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":"1812.01487","created_at":"2026-05-17T23:53:49.965963+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01487v2","created_at":"2026-05-17T23:53:49.965963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01487","created_at":"2026-05-17T23:53:49.965963+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIS7JSXN2KNQ","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIS7JSXN2KNQMC2Q","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIS7JSXN","created_at":"2026-05-18T12:32:19.392346+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/DIS7JSXN2KNQMC2QTAHS63MDAK","json":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK.json","graph_json":"https://pith.science/api/pith-number/DIS7JSXN2KNQMC2QTAHS63MDAK/graph.json","events_json":"https://pith.science/api/pith-number/DIS7JSXN2KNQMC2QTAHS63MDAK/events.json","paper":"https://pith.science/paper/DIS7JSXN"},"agent_actions":{"view_html":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK","download_json":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK.json","view_paper":"https://pith.science/paper/DIS7JSXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01487&json=true","fetch_graph":"https://pith.science/api/pith-number/DIS7JSXN2KNQMC2QTAHS63MDAK/graph.json","fetch_events":"https://pith.science/api/pith-number/DIS7JSXN2KNQMC2QTAHS63MDAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK/action/storage_attestation","attest_author":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK/action/author_attestation","sign_citation":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK/action/citation_signature","submit_replication":"https://pith.science/pith/DIS7JSXN2KNQMC2QTAHS63MDAK/action/replication_record"}},"created_at":"2026-05-17T23:53:49.965963+00:00","updated_at":"2026-05-17T23:53:49.965963+00:00"}