{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J5YDRWETAHAX4WKTC3QQVCVVWT","short_pith_number":"pith:J5YDRWET","schema_version":"1.0","canonical_sha256":"4f7038d89301c17e595316e10a8ab5b4db2640e14ac4e08c0a38beacb97c0f92","source":{"kind":"arxiv","id":"2502.14172","version":2},"attestation_state":"computed","paper":{"title":"A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kaicheng Jin, Liangyu Zhang, Yang Peng, Zhihua Zhang","submitted_at":"2025-02-20T00:53:22Z","abstract_excerpt":"In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The aim of distributional TD learning is to estimate the return distribution of a discounted Markov decision process for a given policy {\\pi}. Previous works on statistical analysis of distributional TD learning mainly focus on the tabular case. In contrast, we first consider the linear function approximation setting and derive sharp finite-sample rates. Our theoretical results demonstrate that the sample complexity of linear distributional TD lear"},"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":"2502.14172","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-20T00:53:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3d7d8da93cb5cbf28b282603e08d529885da93d9afa3069d4bc4d9cca5f35be9","abstract_canon_sha256":"c3b15b1aa3cb3036118440991d2b7541cdac1fcb34bf3f9b2506a44453844d23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:18.275775Z","signature_b64":"MQ9rmjDQs58j9XhkrBW4o52XiayiUkHTmZ8yHtK0Qnavv66ZMa65clPEPWgS61MXjUyh3m/P2pTxFiH44ONADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f7038d89301c17e595316e10a8ab5b4db2640e14ac4e08c0a38beacb97c0f92","last_reissued_at":"2026-07-05T11:02:18.275262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:18.275262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kaicheng Jin, Liangyu Zhang, Yang Peng, Zhihua Zhang","submitted_at":"2025-02-20T00:53:22Z","abstract_excerpt":"In this paper, we study the finite-sample statistical rates of distributional temporal difference (TD) learning with linear function approximation. The aim of distributional TD learning is to estimate the return distribution of a discounted Markov decision process for a given policy {\\pi}. Previous works on statistical analysis of distributional TD learning mainly focus on the tabular case. In contrast, we first consider the linear function approximation setting and derive sharp finite-sample rates. Our theoretical results demonstrate that the sample complexity of linear distributional TD lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14172","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/2502.14172/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":"2502.14172","created_at":"2026-07-05T11:02:18.275323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14172v2","created_at":"2026-07-05T11:02:18.275323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14172","created_at":"2026-07-05T11:02:18.275323+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5YDRWETAHAX","created_at":"2026-07-05T11:02:18.275323+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5YDRWETAHAX4WKT","created_at":"2026-07-05T11:02:18.275323+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5YDRWET","created_at":"2026-07-05T11:02:18.275323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08444","citing_title":"Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11289","citing_title":"Quotient-Categorical Representations for Bellman-Compatible Average-Reward Distributional Reinforcement Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06866","citing_title":"A Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J5YDRWETAHAX4WKTC3QQVCVVWT","json":"https://pith.science/pith/J5YDRWETAHAX4WKTC3QQVCVVWT.json","graph_json":"https://pith.science/api/pith-number/J5YDRWETAHAX4WKTC3QQVCVVWT/graph.json","events_json":"https://pith.science/api/pith-number/J5YDRWETAHAX4WKTC3QQVCVVWT/events.json","paper":"https://pith.science/paper/J5YDRWET"},"agent_actions":{"view_html":"https://pith.science/pith/J5YDRWETAHAX4WKTC3QQVCVVWT","download_json":"https://pith.science/pith/J5YDRWETAHAX4WKTC3QQVCVVWT.json","view_paper":"https://pith.science/paper/J5YDRWET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14172&json=true","fetch_graph":"https://pith.science/api/pith-number/J5YDRWETAHAX4WKTC3QQVCVVWT/graph.json","fetch_events":"https://pith.science/api/pith-number/J5YDRWETAHAX4WKTC3QQVCVVWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5YDRWETAHAX4WKTC3QQVCVVWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5YDRWETAHAX4WKTC3QQVCVVWT/action/storage_attestation","attest_author":"https://pith.science/pith/J5YDRWETAHAX4WKTC3QQVCVVWT/action/author_attestation","sign_citation":"https://pith.science/pith/J5YDRWETAHAX4WKTC3QQVCVVWT/action/citation_signature","submit_replication":"https://pith.science/pith/J5YDRWETAHAX4WKTC3QQVCVVWT/action/replication_record"}},"created_at":"2026-07-05T11:02:18.275323+00:00","updated_at":"2026-07-05T11:02:18.275323+00:00"}