{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2OTVJDKLI6VMGOI5U3T26BDKZ2","short_pith_number":"pith:2OTVJDKL","schema_version":"1.0","canonical_sha256":"d3a7548d4b47aac3391da6e7af046aceb11d61d3f74de37184172a4dc0f5080b","source":{"kind":"arxiv","id":"2209.11745","version":4},"attestation_state":"computed","paper":{"title":"Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Fan Chen, Song Mei, Yu Bai","submitted_at":"2022-09-23T17:47:24Z","abstract_excerpt":"Modern Reinforcement Learning (RL) is more than just learning the optimal policy; Alternative learning goals such as exploring the environment, estimating the underlying model, and learning from preference feedback are all of practical importance. While provably sample-efficient algorithms for each specific goal have been proposed, these algorithms often depend strongly on the particular learning goal and thus admit different structures correspondingly. It is an urging open question whether these learning goals can rather be tackled by a single unified algorithm.\n  We make progress on this que"},"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":"2209.11745","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-23T17:47:24Z","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"f1475f300eb208ca2aa016f37f86e794f4a850fd8dacce38c17356dedbeed7bf","abstract_canon_sha256":"c5bfe157645efa8b52a65c8de91c793cf8f82d50e08cd6e6f7e18b1001d73272"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:55.784174Z","signature_b64":"bb48Oet4ZUmEzz/pgnuph1unMHemZ+1MM30pmLz6o9O7//xfY4OXPLtDNeYS9wKbkZ8Lnncm4er5ZANwZkCjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3a7548d4b47aac3391da6e7af046aceb11d61d3f74de37184172a4dc0f5080b","last_reissued_at":"2026-07-05T09:52:55.783693Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:55.783693Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Fan Chen, Song Mei, Yu Bai","submitted_at":"2022-09-23T17:47:24Z","abstract_excerpt":"Modern Reinforcement Learning (RL) is more than just learning the optimal policy; Alternative learning goals such as exploring the environment, estimating the underlying model, and learning from preference feedback are all of practical importance. While provably sample-efficient algorithms for each specific goal have been proposed, these algorithms often depend strongly on the particular learning goal and thus admit different structures correspondingly. It is an urging open question whether these learning goals can rather be tackled by a single unified algorithm.\n  We make progress on this que"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11745","kind":"arxiv","version":4},"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/2209.11745/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":"2209.11745","created_at":"2026-07-05T09:52:55.783749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.11745v4","created_at":"2026-07-05T09:52:55.783749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11745","created_at":"2026-07-05T09:52:55.783749+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OTVJDKLI6VM","created_at":"2026-07-05T09:52:55.783749+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OTVJDKLI6VMGOI5","created_at":"2026-07-05T09:52:55.783749+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OTVJDKL","created_at":"2026-07-05T09:52:55.783749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29645","citing_title":"The Sample Complexity of Multiclass and Sparse Contextual Bandits","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03125","citing_title":"Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2OTVJDKLI6VMGOI5U3T26BDKZ2","json":"https://pith.science/pith/2OTVJDKLI6VMGOI5U3T26BDKZ2.json","graph_json":"https://pith.science/api/pith-number/2OTVJDKLI6VMGOI5U3T26BDKZ2/graph.json","events_json":"https://pith.science/api/pith-number/2OTVJDKLI6VMGOI5U3T26BDKZ2/events.json","paper":"https://pith.science/paper/2OTVJDKL"},"agent_actions":{"view_html":"https://pith.science/pith/2OTVJDKLI6VMGOI5U3T26BDKZ2","download_json":"https://pith.science/pith/2OTVJDKLI6VMGOI5U3T26BDKZ2.json","view_paper":"https://pith.science/paper/2OTVJDKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.11745&json=true","fetch_graph":"https://pith.science/api/pith-number/2OTVJDKLI6VMGOI5U3T26BDKZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/2OTVJDKLI6VMGOI5U3T26BDKZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OTVJDKLI6VMGOI5U3T26BDKZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OTVJDKLI6VMGOI5U3T26BDKZ2/action/storage_attestation","attest_author":"https://pith.science/pith/2OTVJDKLI6VMGOI5U3T26BDKZ2/action/author_attestation","sign_citation":"https://pith.science/pith/2OTVJDKLI6VMGOI5U3T26BDKZ2/action/citation_signature","submit_replication":"https://pith.science/pith/2OTVJDKLI6VMGOI5U3T26BDKZ2/action/replication_record"}},"created_at":"2026-07-05T09:52:55.783749+00:00","updated_at":"2026-07-05T09:52:55.783749+00:00"}