{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OELCJO7SCKVBKJD5RRQYP4IG6M","short_pith_number":"pith:OELCJO7S","schema_version":"1.0","canonical_sha256":"711624bbf212aa15247d8c6187f106f31a0b57a25cf0c901d5c42402e3bffb5b","source":{"kind":"arxiv","id":"2403.10855","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Options and State Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Ayoub Ghriss, Masashi Sugiyama","submitted_at":"2024-03-16T08:30:55Z","abstract_excerpt":"The current thesis aims to explore the reinforcement learning field and build on existing methods to produce improved ones to tackle the problem of learning in high-dimensional and complex environments. It addresses such goals by decomposing learning tasks in a hierarchical fashion known as Hierarchical Reinforcement Learning.\n  We start in the first chapter by getting familiar with the Markov Decision Process framework and presenting some of its recent techniques that the following chapters use. We then proceed to build our Hierarchical Policy learning as an answer to the limitations of a sin"},"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":"2403.10855","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-16T08:30:55Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"2929f5240178403b563d78d40f4faf4eb220e57817cde76758e1ac4af5104b54","abstract_canon_sha256":"9ce2b091b0f69373ce368b6cb5810c2d8b5ebfce11639e4d422482c0048ae269"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:00:03.889504Z","signature_b64":"g/Soa7obC2GDhlHewZCBDiG/0uFsdaHcxUI7Ex5VTBHOy0eeHB3082O4pz77fGOsfOBrWBTOSn72aiP1sH2XDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"711624bbf212aa15247d8c6187f106f31a0b57a25cf0c901d5c42402e3bffb5b","last_reissued_at":"2026-07-05T08:00:03.889050Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:00:03.889050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Options and State Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Ayoub Ghriss, Masashi Sugiyama","submitted_at":"2024-03-16T08:30:55Z","abstract_excerpt":"The current thesis aims to explore the reinforcement learning field and build on existing methods to produce improved ones to tackle the problem of learning in high-dimensional and complex environments. It addresses such goals by decomposing learning tasks in a hierarchical fashion known as Hierarchical Reinforcement Learning.\n  We start in the first chapter by getting familiar with the Markov Decision Process framework and presenting some of its recent techniques that the following chapters use. We then proceed to build our Hierarchical Policy learning as an answer to the limitations of a sin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10855","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.10855/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":"2403.10855","created_at":"2026-07-05T08:00:03.889102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10855v2","created_at":"2026-07-05T08:00:03.889102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10855","created_at":"2026-07-05T08:00:03.889102+00:00"},{"alias_kind":"pith_short_12","alias_value":"OELCJO7SCKVB","created_at":"2026-07-05T08:00:03.889102+00:00"},{"alias_kind":"pith_short_16","alias_value":"OELCJO7SCKVBKJD5","created_at":"2026-07-05T08:00:03.889102+00:00"},{"alias_kind":"pith_short_8","alias_value":"OELCJO7S","created_at":"2026-07-05T08:00:03.889102+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/OELCJO7SCKVBKJD5RRQYP4IG6M","json":"https://pith.science/pith/OELCJO7SCKVBKJD5RRQYP4IG6M.json","graph_json":"https://pith.science/api/pith-number/OELCJO7SCKVBKJD5RRQYP4IG6M/graph.json","events_json":"https://pith.science/api/pith-number/OELCJO7SCKVBKJD5RRQYP4IG6M/events.json","paper":"https://pith.science/paper/OELCJO7S"},"agent_actions":{"view_html":"https://pith.science/pith/OELCJO7SCKVBKJD5RRQYP4IG6M","download_json":"https://pith.science/pith/OELCJO7SCKVBKJD5RRQYP4IG6M.json","view_paper":"https://pith.science/paper/OELCJO7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10855&json=true","fetch_graph":"https://pith.science/api/pith-number/OELCJO7SCKVBKJD5RRQYP4IG6M/graph.json","fetch_events":"https://pith.science/api/pith-number/OELCJO7SCKVBKJD5RRQYP4IG6M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OELCJO7SCKVBKJD5RRQYP4IG6M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OELCJO7SCKVBKJD5RRQYP4IG6M/action/storage_attestation","attest_author":"https://pith.science/pith/OELCJO7SCKVBKJD5RRQYP4IG6M/action/author_attestation","sign_citation":"https://pith.science/pith/OELCJO7SCKVBKJD5RRQYP4IG6M/action/citation_signature","submit_replication":"https://pith.science/pith/OELCJO7SCKVBKJD5RRQYP4IG6M/action/replication_record"}},"created_at":"2026-07-05T08:00:03.889102+00:00","updated_at":"2026-07-05T08:00:03.889102+00:00"}