{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FNFUNRZ7S2AVUKENGNUBX7PDCZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e6f3f5636487705e24e63328d5b6477fad2626ecd796ce8c5caf7119f6a58729","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T07:01:28Z","title_canon_sha256":"621fb219124f31f75158de11676033afb0b621f92fd4ef63d5cab1673649b15c"},"schema_version":"1.0","source":{"id":"2411.00401","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00401","created_at":"2026-07-05T11:03:53Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00401v2","created_at":"2026-07-05T11:03:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00401","created_at":"2026-07-05T11:03:53Z"},{"alias_kind":"pith_short_12","alias_value":"FNFUNRZ7S2AV","created_at":"2026-07-05T11:03:53Z"},{"alias_kind":"pith_short_16","alias_value":"FNFUNRZ7S2AVUKEN","created_at":"2026-07-05T11:03:53Z"},{"alias_kind":"pith_short_8","alias_value":"FNFUNRZ7","created_at":"2026-07-05T11:03:53Z"}],"graph_snapshots":[{"event_id":"sha256:1a4f5adfb1708552a0e60fbfedab84afa3ec741e7fbbb02866e65b07858be91f","target":"graph","created_at":"2026-07-05T11:03:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.00401/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T07:01:28Z","title":"Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00401","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3cb94429077466a6f317e1765f8da00ccf2dc2f6fc650f0d5f5e596cf172a997","target":"record","created_at":"2026-07-05T11:03:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e6f3f5636487705e24e63328d5b6477fad2626ecd796ce8c5caf7119f6a58729","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T07:01:28Z","title_canon_sha256":"621fb219124f31f75158de11676033afb0b621f92fd4ef63d5cab1673649b15c"},"schema_version":"1.0","source":{"id":"2411.00401","kind":"arxiv","version":2}},"canonical_sha256":"2b4b46c73f96815a288d33681bfde316618f76f5a46d3909a87a1fbc1e75afd1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b4b46c73f96815a288d33681bfde316618f76f5a46d3909a87a1fbc1e75afd1","first_computed_at":"2026-07-05T11:03:53.389460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:53.389460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"54jwXFR6urcxFImsn9uWzx6cmvXDe0sQNfcwfnF3MBFoG9DEa8byQGTILaAeVA3KicrHR0KCN7b1lAfLVOgTCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:53.390003Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00401","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cb94429077466a6f317e1765f8da00ccf2dc2f6fc650f0d5f5e596cf172a997","sha256:1a4f5adfb1708552a0e60fbfedab84afa3ec741e7fbbb02866e65b07858be91f"],"state_sha256":"b882d49b13a16914cbd583be974b61746fb5c8acf177891610d111da4b29c5eb"}