{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NHGF75XPPOQ7TQMRDRWH3E5KED","short_pith_number":"pith:NHGF75XP","schema_version":"1.0","canonical_sha256":"69cc5ff6ef7ba1f9c1911c6c7d93aa20ce30f2163dd43f7723985f1ab5e9d24e","source":{"kind":"arxiv","id":"2501.10598","version":3},"attestation_state":"computed","paper":{"title":"Addressing Finite-Horizon MDPs via Low-Rank Tensor Value Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio G. Marques, Jose Luis Orejuela, Sergio Rozada","submitted_at":"2025-01-17T23:10:50Z","abstract_excerpt":"We study the problem of learning optimal policies in finite-horizon Markov Decision Processes (MDPs) using low-rank reinforcement learning (RL) methods. In finite-horizon MDPs, the policies, and therefore the value functions (VFs) are not stationary. This aggravates the challenges of high-dimensional MDPs, as they suffer from the curse of dimensionality and high sample complexity. To address these issues, we propose modeling the VFs of finite-horizon MDPs as low-rank tensors, enabling a scalable representation that renders the problem of learning optimal policies tractable. Our approach focuse"},"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":"2501.10598","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T23:10:50Z","cross_cats_sorted":[],"title_canon_sha256":"d458e51a2f597be865a64c5aa8e381f65cb169bf785e54c38b5d5a63b3254d84","abstract_canon_sha256":"5d3683d8381e9483437f9a1586c47f534cf458b81377a05e09ad66d135ef9690"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:14.605308Z","signature_b64":"ZSYLcIVfaS0hw3FPiqKI9uj+r1fC4qC8lUu8M3Q+7uOGJCs5Djy2PmY/eLoJW4I1qaizND+sclx2zWaY6YAbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69cc5ff6ef7ba1f9c1911c6c7d93aa20ce30f2163dd43f7723985f1ab5e9d24e","last_reissued_at":"2026-05-18T02:45:14.604653Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:14.604653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Addressing Finite-Horizon MDPs via Low-Rank Tensor Value Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonio G. Marques, Jose Luis Orejuela, Sergio Rozada","submitted_at":"2025-01-17T23:10:50Z","abstract_excerpt":"We study the problem of learning optimal policies in finite-horizon Markov Decision Processes (MDPs) using low-rank reinforcement learning (RL) methods. In finite-horizon MDPs, the policies, and therefore the value functions (VFs) are not stationary. This aggravates the challenges of high-dimensional MDPs, as they suffer from the curse of dimensionality and high sample complexity. To address these issues, we propose modeling the VFs of finite-horizon MDPs as low-rank tensors, enabling a scalable representation that renders the problem of learning optimal policies tractable. Our approach focuse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10598","kind":"arxiv","version":3},"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":"2501.10598","created_at":"2026-05-18T02:45:14.604756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10598v3","created_at":"2026-05-18T02:45:14.604756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10598","created_at":"2026-05-18T02:45:14.604756+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHGF75XPPOQ7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHGF75XPPOQ7TQMR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHGF75XP","created_at":"2026-05-18T12:33:37.589309+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/NHGF75XPPOQ7TQMRDRWH3E5KED","json":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED.json","graph_json":"https://pith.science/api/pith-number/NHGF75XPPOQ7TQMRDRWH3E5KED/graph.json","events_json":"https://pith.science/api/pith-number/NHGF75XPPOQ7TQMRDRWH3E5KED/events.json","paper":"https://pith.science/paper/NHGF75XP"},"agent_actions":{"view_html":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED","download_json":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED.json","view_paper":"https://pith.science/paper/NHGF75XP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10598&json=true","fetch_graph":"https://pith.science/api/pith-number/NHGF75XPPOQ7TQMRDRWH3E5KED/graph.json","fetch_events":"https://pith.science/api/pith-number/NHGF75XPPOQ7TQMRDRWH3E5KED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED/action/storage_attestation","attest_author":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED/action/author_attestation","sign_citation":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED/action/citation_signature","submit_replication":"https://pith.science/pith/NHGF75XPPOQ7TQMRDRWH3E5KED/action/replication_record"}},"created_at":"2026-05-18T02:45:14.604756+00:00","updated_at":"2026-05-18T02:45:14.604756+00:00"}