{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:TRZNPCSSVQZQRLHIP577ZJXRJG","short_pith_number":"pith:TRZNPCSS","schema_version":"1.0","canonical_sha256":"9c72d78a52ac3308ace87f7ffca6f1499a4c600c36b2c829b7471e190c0ef36f","source":{"kind":"arxiv","id":"1202.3717","version":1},"attestation_state":"computed","paper":{"title":"PAC-Bayesian Policy Evaluation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Csaba Szepesvari, Joelle Pineau, Mahdi MIlani Fard","submitted_at":"2012-02-14T16:41:17Z","abstract_excerpt":"Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, largely depends on accuracy and correctness of these priors. PAC-Bayesian methods overcome this problem by providing bounds that hold regardless of the correctness of the prior distribution. This paper introduces the first PAC-Bayesian bound for the batch reinforcement learning problem with function approximation. We show how this bound can be used to perform model-selection in a transfer learning scenario. Our empirical "},"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":"1202.3717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-14T16:41:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a6c3060f6b8115ae6b05f71d0e05b34b69b7ff9e8afc3fb87f723df1df057256","abstract_canon_sha256":"d618e8fa420865fd56bcb075231106e2e9508dffd9bfbdfa132579f02867e638"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:02:03.379058Z","signature_b64":"aICBf714jmsaqhx8qCR3+6/2gCP8KBOULkNDtYprbQ08mkJ4274qrYVD9H25SvYHHlnaDOTr5+lmGgcKTECVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c72d78a52ac3308ace87f7ffca6f1499a4c600c36b2c829b7471e190c0ef36f","last_reissued_at":"2026-05-18T04:02:03.378343Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:02:03.378343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAC-Bayesian Policy Evaluation for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Csaba Szepesvari, Joelle Pineau, Mahdi MIlani Fard","submitted_at":"2012-02-14T16:41:17Z","abstract_excerpt":"Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, largely depends on accuracy and correctness of these priors. PAC-Bayesian methods overcome this problem by providing bounds that hold regardless of the correctness of the prior distribution. This paper introduces the first PAC-Bayesian bound for the batch reinforcement learning problem with function approximation. We show how this bound can be used to perform model-selection in a transfer learning scenario. Our empirical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.3717","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":""},"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":"1202.3717","created_at":"2026-05-18T04:02:03.378451+00:00"},{"alias_kind":"arxiv_version","alias_value":"1202.3717v1","created_at":"2026-05-18T04:02:03.378451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.3717","created_at":"2026-05-18T04:02:03.378451+00:00"},{"alias_kind":"pith_short_12","alias_value":"TRZNPCSSVQZQ","created_at":"2026-05-18T12:27:23.164592+00:00"},{"alias_kind":"pith_short_16","alias_value":"TRZNPCSSVQZQRLHI","created_at":"2026-05-18T12:27:23.164592+00:00"},{"alias_kind":"pith_short_8","alias_value":"TRZNPCSS","created_at":"2026-05-18T12:27:23.164592+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/TRZNPCSSVQZQRLHIP577ZJXRJG","json":"https://pith.science/pith/TRZNPCSSVQZQRLHIP577ZJXRJG.json","graph_json":"https://pith.science/api/pith-number/TRZNPCSSVQZQRLHIP577ZJXRJG/graph.json","events_json":"https://pith.science/api/pith-number/TRZNPCSSVQZQRLHIP577ZJXRJG/events.json","paper":"https://pith.science/paper/TRZNPCSS"},"agent_actions":{"view_html":"https://pith.science/pith/TRZNPCSSVQZQRLHIP577ZJXRJG","download_json":"https://pith.science/pith/TRZNPCSSVQZQRLHIP577ZJXRJG.json","view_paper":"https://pith.science/paper/TRZNPCSS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1202.3717&json=true","fetch_graph":"https://pith.science/api/pith-number/TRZNPCSSVQZQRLHIP577ZJXRJG/graph.json","fetch_events":"https://pith.science/api/pith-number/TRZNPCSSVQZQRLHIP577ZJXRJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TRZNPCSSVQZQRLHIP577ZJXRJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TRZNPCSSVQZQRLHIP577ZJXRJG/action/storage_attestation","attest_author":"https://pith.science/pith/TRZNPCSSVQZQRLHIP577ZJXRJG/action/author_attestation","sign_citation":"https://pith.science/pith/TRZNPCSSVQZQRLHIP577ZJXRJG/action/citation_signature","submit_replication":"https://pith.science/pith/TRZNPCSSVQZQRLHIP577ZJXRJG/action/replication_record"}},"created_at":"2026-05-18T04:02:03.378451+00:00","updated_at":"2026-05-18T04:02:03.378451+00:00"}