{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UXHSCFCO3TNYMOKXHH65NQTUCI","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":"290fe73b0780a99f669dd3a2fd6c2127101d3719018c221c47e9e5947d958c95","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-21T00:43:24Z","title_canon_sha256":"f262ace0d0fccc25885846e200d5d6c32e51695857b0dbe0b492f99fff34e783"},"schema_version":"1.0","source":{"id":"1711.07979","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.07979","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"arxiv_version","alias_value":"1711.07979v3","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07979","created_at":"2026-05-18T00:02:39Z"},{"alias_kind":"pith_short_12","alias_value":"UXHSCFCO3TNY","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"UXHSCFCO3TNYMOKX","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"UXHSCFCO","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:aed51dd2b932c55902d61ba654172e68e0e941a2fd3045dddac2c7b85143305d","target":"graph","created_at":"2026-05-18T00:02:39Z","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"},"paper":{"abstract_excerpt":"We propose a practical non-episodic PSRL algorithm that unlike recent state-of-the-art PSRL algorithms uses a deterministic, model-independent episode switching schedule. Our algorithm termed deterministic schedule PSRL (DS-PSRL) is efficient in terms of time, sample, and space complexity. We prove a Bayesian regret bound under mild assumptions. Our result is more generally applicable to multiple parameters and continuous state action problems. We compare our algorithm with state-of-the-art PSRL algorithms on standard discrete and continuous problems from the literature. Finally, we show how t","authors_text":"Georgios Theocharous, Nikos Vlassis, Yasin Abbasi-Yadkori, Zheng Wen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-21T00:43:24Z","title":"Posterior Sampling for Large Scale Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07979","kind":"arxiv","version":3},"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":"sha256:07998a5558e9c6e4c0c0e0ebe2e93a4ab0dcee4bfe1bbbc378b687941022dc63","target":"record","created_at":"2026-05-18T00:02:39Z","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":"290fe73b0780a99f669dd3a2fd6c2127101d3719018c221c47e9e5947d958c95","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-21T00:43:24Z","title_canon_sha256":"f262ace0d0fccc25885846e200d5d6c32e51695857b0dbe0b492f99fff34e783"},"schema_version":"1.0","source":{"id":"1711.07979","kind":"arxiv","version":3}},"canonical_sha256":"a5cf21144edcdb86395739fdd6c274123af16ecad42c96ea9a411d099920c2f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5cf21144edcdb86395739fdd6c274123af16ecad42c96ea9a411d099920c2f6","first_computed_at":"2026-05-18T00:02:39.771244Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:39.771244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YIebDbk8N59riXq68ZBYLpAx6/oATGkYWMP85cDx+wwK85ChKpcnDM54VPi7jIK9zIx08Y88XCMQpgSQEN81BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:39.771912Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.07979","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07998a5558e9c6e4c0c0e0ebe2e93a4ab0dcee4bfe1bbbc378b687941022dc63","sha256:aed51dd2b932c55902d61ba654172e68e0e941a2fd3045dddac2c7b85143305d"],"state_sha256":"412c331db6d73654c7e528469e57a2a19a118de2d41f7df0b6ad08aae62f1927"}