{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:3GLMN7R6E6LHRFKFSTOQ7SA7IQ","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":"647fc37620e5d2b31d1448edbb068f3c8447470607f07302169aff3f56f4d939","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-20T20:40:47Z","title_canon_sha256":"148e6d0299d4c7d43e18646e20cdc4ab620374982428659ff59f97fc67a6eed0"},"schema_version":"1.0","source":{"id":"2210.11579","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.11579","created_at":"2026-07-05T05:08:55Z"},{"alias_kind":"arxiv_version","alias_value":"2210.11579v1","created_at":"2026-07-05T05:08:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11579","created_at":"2026-07-05T05:08:55Z"},{"alias_kind":"pith_short_12","alias_value":"3GLMN7R6E6LH","created_at":"2026-07-05T05:08:55Z"},{"alias_kind":"pith_short_16","alias_value":"3GLMN7R6E6LHRFKF","created_at":"2026-07-05T05:08:55Z"},{"alias_kind":"pith_short_8","alias_value":"3GLMN7R6","created_at":"2026-07-05T05:08:55Z"}],"graph_snapshots":[{"event_id":"sha256:a0b3a39f46de43cba9181023479187f651b82373b55e87335d75c1ed2e2324db","target":"graph","created_at":"2026-07-05T05:08:55Z","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/2210.11579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a model-based lifelong reinforcement-learning approach that estimates a hierarchical Bayesian posterior distilling the common structure shared across different tasks. The learned posterior combined with a sample-based Bayesian exploration procedure increases the sample efficiency of learning across a family of related tasks. We first derive an analysis of the relationship between the sample complexity and the initialization quality of the posterior in the finite MDP setting. We next scale the approach to continuous-state domains by introducing a Variational Bayesian Lifelong Reinfor","authors_text":"George Konidaris, Haotian Fu, Michael Littman, Shangqun Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-20T20:40:47Z","title":"Model-based Lifelong Reinforcement Learning with Bayesian Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11579","kind":"arxiv","version":1},"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:ebd13ca39b8e96724d2d0e75ba5393239e2adc2042e7726de705498c1447ef16","target":"record","created_at":"2026-07-05T05:08:55Z","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":"647fc37620e5d2b31d1448edbb068f3c8447470607f07302169aff3f56f4d939","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-20T20:40:47Z","title_canon_sha256":"148e6d0299d4c7d43e18646e20cdc4ab620374982428659ff59f97fc67a6eed0"},"schema_version":"1.0","source":{"id":"2210.11579","kind":"arxiv","version":1}},"canonical_sha256":"d996c6fe3e279678954594dd0fc81f441ce7b0ba1207793706a050c72d6e80d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d996c6fe3e279678954594dd0fc81f441ce7b0ba1207793706a050c72d6e80d8","first_computed_at":"2026-07-05T05:08:55.182180Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:55.182180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gVsFSprPEq//xgJUfKjW9PzlrvtN1is6UoZhXvLX+yLn079f2DLNEMqgEmE7VQ+wJ/HUrje8S/vk2Hk77zoNDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:55.182572Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.11579","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebd13ca39b8e96724d2d0e75ba5393239e2adc2042e7726de705498c1447ef16","sha256:a0b3a39f46de43cba9181023479187f651b82373b55e87335d75c1ed2e2324db"],"state_sha256":"634298fddefbc25a9567e70b2543da73b35f0a1cf5ef8f1dc468278246a59a4c"}