{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:46ZXZ573E66L5H4FXBLWDYA6XC","short_pith_number":"pith:46ZXZ573","schema_version":"1.0","canonical_sha256":"e7b37cf7fb27bcbe9f85b85761e01eb8b6f8cc9917fb295b508a8e903a28f5bd","source":{"kind":"arxiv","id":"2110.14798","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Alessandro Lazaric, Andrea Tirinzoni, Marcello Restelli, Matteo Papini, Matteo Pirotta","submitted_at":"2021-10-27T22:07:08Z","abstract_excerpt":"We study the role of the representation of state-action value functions in regret minimization in finite-horizon Markov Decision Processes (MDPs) with linear structure. We first derive a necessary condition on the representation, called universally spanning optimal features (UNISOFT), to achieve constant regret in any MDP with linear reward function. This result encompasses the well-known settings of low-rank MDPs and, more generally, zero inherent Bellman error (also known as the Bellman closure assumption). We then demonstrate that this condition is also sufficient for these classes of probl"},"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":"2110.14798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-27T22:07:08Z","cross_cats_sorted":[],"title_canon_sha256":"13fd406ced8859f0788c1a3d87e688aaf903afe60e640ecba0d1184af3789f1d","abstract_canon_sha256":"9b4733b915bbddd881d477580a124cfa22f2fc509921135673048c972fbb04b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:47.325001Z","signature_b64":"4aYnc7sNXg4KDkJ8e8XgF2ctLA44nXEbIKzcZ6TbW/ZaLg737O50sxPxt3AVvIPxZb2ZewBpnGiAqXK1IrmaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7b37cf7fb27bcbe9f85b85761e01eb8b6f8cc9917fb295b508a8e903a28f5bd","last_reissued_at":"2026-07-05T03:26:47.324576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:47.324576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Alessandro Lazaric, Andrea Tirinzoni, Marcello Restelli, Matteo Papini, Matteo Pirotta","submitted_at":"2021-10-27T22:07:08Z","abstract_excerpt":"We study the role of the representation of state-action value functions in regret minimization in finite-horizon Markov Decision Processes (MDPs) with linear structure. We first derive a necessary condition on the representation, called universally spanning optimal features (UNISOFT), to achieve constant regret in any MDP with linear reward function. This result encompasses the well-known settings of low-rank MDPs and, more generally, zero inherent Bellman error (also known as the Bellman closure assumption). We then demonstrate that this condition is also sufficient for these classes of probl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.14798","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/2110.14798/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":"2110.14798","created_at":"2026-07-05T03:26:47.324637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.14798v1","created_at":"2026-07-05T03:26:47.324637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.14798","created_at":"2026-07-05T03:26:47.324637+00:00"},{"alias_kind":"pith_short_12","alias_value":"46ZXZ573E66L","created_at":"2026-07-05T03:26:47.324637+00:00"},{"alias_kind":"pith_short_16","alias_value":"46ZXZ573E66L5H4F","created_at":"2026-07-05T03:26:47.324637+00:00"},{"alias_kind":"pith_short_8","alias_value":"46ZXZ573","created_at":"2026-07-05T03:26:47.324637+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/46ZXZ573E66L5H4FXBLWDYA6XC","json":"https://pith.science/pith/46ZXZ573E66L5H4FXBLWDYA6XC.json","graph_json":"https://pith.science/api/pith-number/46ZXZ573E66L5H4FXBLWDYA6XC/graph.json","events_json":"https://pith.science/api/pith-number/46ZXZ573E66L5H4FXBLWDYA6XC/events.json","paper":"https://pith.science/paper/46ZXZ573"},"agent_actions":{"view_html":"https://pith.science/pith/46ZXZ573E66L5H4FXBLWDYA6XC","download_json":"https://pith.science/pith/46ZXZ573E66L5H4FXBLWDYA6XC.json","view_paper":"https://pith.science/paper/46ZXZ573","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.14798&json=true","fetch_graph":"https://pith.science/api/pith-number/46ZXZ573E66L5H4FXBLWDYA6XC/graph.json","fetch_events":"https://pith.science/api/pith-number/46ZXZ573E66L5H4FXBLWDYA6XC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46ZXZ573E66L5H4FXBLWDYA6XC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46ZXZ573E66L5H4FXBLWDYA6XC/action/storage_attestation","attest_author":"https://pith.science/pith/46ZXZ573E66L5H4FXBLWDYA6XC/action/author_attestation","sign_citation":"https://pith.science/pith/46ZXZ573E66L5H4FXBLWDYA6XC/action/citation_signature","submit_replication":"https://pith.science/pith/46ZXZ573E66L5H4FXBLWDYA6XC/action/replication_record"}},"created_at":"2026-07-05T03:26:47.324637+00:00","updated_at":"2026-07-05T03:26:47.324637+00:00"}