{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FNFUNRZ7S2AVUKENGNUBX7PDCZ","short_pith_number":"pith:FNFUNRZ7","schema_version":"1.0","canonical_sha256":"2b4b46c73f96815a288d33681bfde316618f76f5a46d3909a87a1fbc1e75afd1","source":{"kind":"arxiv","id":"2411.00401","version":2},"attestation_state":"computed","paper":{"title":"Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chris Chow, Eric Hanchen Jiang, Furong Huang, Han Liu, Haochen Zhang, Oscar Hernan Madrid Padilla, Yanchao Sun, Yasi Zhang, Yuchen Cui, Zhi Zhang","submitted_at":"2024-11-01T07:01:28Z","abstract_excerpt":"Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings. In lifelong RL, the \"life\" of an RL agent is modeled as a stream of tasks drawn from a task distribution. We propose EPIC (Empirical PAC-Bayes that Improves Continuously), a novel algorithm designed for lifelong RL using PAC-Bayes theory. EPIC learns a shared policy distribution, referred to as the world policy, which enables rapid adaptation to new tasks while retaining valuable knowledge from previous experiences. Our theoretical analysis establishes a relat"},"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":"2411.00401","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T07:01:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"621fb219124f31f75158de11676033afb0b621f92fd4ef63d5cab1673649b15c","abstract_canon_sha256":"e6f3f5636487705e24e63328d5b6477fad2626ecd796ce8c5caf7119f6a58729"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:53.390003Z","signature_b64":"54jwXFR6urcxFImsn9uWzx6cmvXDe0sQNfcwfnF3MBFoG9DEa8byQGTILaAeVA3KicrHR0KCN7b1lAfLVOgTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b4b46c73f96815a288d33681bfde316618f76f5a46d3909a87a1fbc1e75afd1","last_reissued_at":"2026-07-05T11:03:53.389460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:53.389460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chris Chow, Eric Hanchen Jiang, Furong Huang, Han Liu, Haochen Zhang, Oscar Hernan Madrid Padilla, Yanchao Sun, Yasi Zhang, Yuchen Cui, Zhi Zhang","submitted_at":"2024-11-01T07:01:28Z","abstract_excerpt":"Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings. In lifelong RL, the \"life\" of an RL agent is modeled as a stream of tasks drawn from a task distribution. We propose EPIC (Empirical PAC-Bayes that Improves Continuously), a novel algorithm designed for lifelong RL using PAC-Bayes theory. EPIC learns a shared policy distribution, referred to as the world policy, which enables rapid adaptation to new tasks while retaining valuable knowledge from previous experiences. Our theoretical analysis establishes a relat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00401","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/2411.00401/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":"2411.00401","created_at":"2026-07-05T11:03:53.389518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00401v2","created_at":"2026-07-05T11:03:53.389518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00401","created_at":"2026-07-05T11:03:53.389518+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNFUNRZ7S2AV","created_at":"2026-07-05T11:03:53.389518+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNFUNRZ7S2AVUKEN","created_at":"2026-07-05T11:03:53.389518+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNFUNRZ7","created_at":"2026-07-05T11:03:53.389518+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/FNFUNRZ7S2AVUKENGNUBX7PDCZ","json":"https://pith.science/pith/FNFUNRZ7S2AVUKENGNUBX7PDCZ.json","graph_json":"https://pith.science/api/pith-number/FNFUNRZ7S2AVUKENGNUBX7PDCZ/graph.json","events_json":"https://pith.science/api/pith-number/FNFUNRZ7S2AVUKENGNUBX7PDCZ/events.json","paper":"https://pith.science/paper/FNFUNRZ7"},"agent_actions":{"view_html":"https://pith.science/pith/FNFUNRZ7S2AVUKENGNUBX7PDCZ","download_json":"https://pith.science/pith/FNFUNRZ7S2AVUKENGNUBX7PDCZ.json","view_paper":"https://pith.science/paper/FNFUNRZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00401&json=true","fetch_graph":"https://pith.science/api/pith-number/FNFUNRZ7S2AVUKENGNUBX7PDCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FNFUNRZ7S2AVUKENGNUBX7PDCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNFUNRZ7S2AVUKENGNUBX7PDCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNFUNRZ7S2AVUKENGNUBX7PDCZ/action/storage_attestation","attest_author":"https://pith.science/pith/FNFUNRZ7S2AVUKENGNUBX7PDCZ/action/author_attestation","sign_citation":"https://pith.science/pith/FNFUNRZ7S2AVUKENGNUBX7PDCZ/action/citation_signature","submit_replication":"https://pith.science/pith/FNFUNRZ7S2AVUKENGNUBX7PDCZ/action/replication_record"}},"created_at":"2026-07-05T11:03:53.389518+00:00","updated_at":"2026-07-05T11:03:53.389518+00:00"}