{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DMLOGIMKBQ5OQ4FVIZ4HX3JW5M","short_pith_number":"pith:DMLOGIMK","canonical_record":{"source":{"id":"1912.06366","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-13T09:10:18Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"da8a3acef53a90a5571056e6bdbf3a6af3bcaca6642aefa5820bd8c054f8c016","abstract_canon_sha256":"29ac0d533a859c398531fe4b90d189a8c658021cab32d4bbe00b611e90b637c0"},"schema_version":"1.0"},"canonical_sha256":"1b16e3218a0c3ae870b546787bed36eb2c5dd1220fbf82434cb057bf1b184ef3","source":{"kind":"arxiv","id":"1912.06366","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.06366","created_at":"2026-07-05T00:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"1912.06366v2","created_at":"2026-07-05T00:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.06366","created_at":"2026-07-05T00:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"DMLOGIMKBQ5O","created_at":"2026-07-05T00:42:22Z"},{"alias_kind":"pith_short_16","alias_value":"DMLOGIMKBQ5OQ4FV","created_at":"2026-07-05T00:42:22Z"},{"alias_kind":"pith_short_8","alias_value":"DMLOGIMK","created_at":"2026-07-05T00:42:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DMLOGIMKBQ5OQ4FVIZ4HX3JW5M","target":"record","payload":{"canonical_record":{"source":{"id":"1912.06366","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-13T09:10:18Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"da8a3acef53a90a5571056e6bdbf3a6af3bcaca6642aefa5820bd8c054f8c016","abstract_canon_sha256":"29ac0d533a859c398531fe4b90d189a8c658021cab32d4bbe00b611e90b637c0"},"schema_version":"1.0"},"canonical_sha256":"1b16e3218a0c3ae870b546787bed36eb2c5dd1220fbf82434cb057bf1b184ef3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:22.259567Z","signature_b64":"tbrn4m674eJIXIucHpuac3socMSJpgxtqs2qNdN26QCZjP5477evbda8UNwTWef8csjSdZ1Z4UnDAVegB1mxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b16e3218a0c3ae870b546787bed36eb2c5dd1220fbf82434cb057bf1b184ef3","last_reissued_at":"2026-07-05T00:42:22.259055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:22.259055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.06366","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:42:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/lROHKzkySHF9hkhSE2tTVxhU6VF1eumBBk8hhPcsP7L0/ZBdPI67xwGseN3M2Rad8G6IK0fqTrT/CW25locCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:06:21.588360Z"},"content_sha256":"e629451c0bb455581b1ac6d9fdd4aad139037c5668576c600cb836f89af8fbb2","schema_version":"1.0","event_id":"sha256:e629451c0bb455581b1ac6d9fdd4aad139037c5668576c600cb836f89af8fbb2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DMLOGIMKBQ5OQ4FVIZ4HX3JW5M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Reinforcement Learning with Aggregated States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Benjamin Van Roy, Shi Dong, Zhengyuan Zhou","submitted_at":"2019-12-13T09:10:18Z","abstract_excerpt":"We establish that an optimistic variant of Q-learning applied to a fixed-horizon episodic Markov decision process with an aggregated state representation incurs regret $\\tilde{\\mathcal{O}}(\\sqrt{H^5 M K} + \\epsilon HK)$, where $H$ is the horizon, $M$ is the number of aggregate states, $K$ is the number of episodes, and $\\epsilon$ is the largest difference between any pair of optimal state-action values associated with a common aggregate state. Notably, this regret bound does not depend on the number of states or actions and indicates that asymptotic per-period regret is no greater than $\\epsil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06366","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/1912.06366/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:42:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JgA0B11OBfs3BPHk84KyHblDvwG6wI9bca192qTgo8cdTcn6qgkqMnIXHDfdGnyORKgLSPVvUuO/F1uvm9raDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:06:21.588959Z"},"content_sha256":"9acc231946899b08c926ee111a2e5cd50cfcc0bc76e6723fffa78eb440d1b44d","schema_version":"1.0","event_id":"sha256:9acc231946899b08c926ee111a2e5cd50cfcc0bc76e6723fffa78eb440d1b44d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DMLOGIMKBQ5OQ4FVIZ4HX3JW5M/bundle.json","state_url":"https://pith.science/pith/DMLOGIMKBQ5OQ4FVIZ4HX3JW5M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DMLOGIMKBQ5OQ4FVIZ4HX3JW5M/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T16:06:21Z","links":{"resolver":"https://pith.science/pith/DMLOGIMKBQ5OQ4FVIZ4HX3JW5M","bundle":"https://pith.science/pith/DMLOGIMKBQ5OQ4FVIZ4HX3JW5M/bundle.json","state":"https://pith.science/pith/DMLOGIMKBQ5OQ4FVIZ4HX3JW5M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DMLOGIMKBQ5OQ4FVIZ4HX3JW5M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DMLOGIMKBQ5OQ4FVIZ4HX3JW5M","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":"29ac0d533a859c398531fe4b90d189a8c658021cab32d4bbe00b611e90b637c0","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-13T09:10:18Z","title_canon_sha256":"da8a3acef53a90a5571056e6bdbf3a6af3bcaca6642aefa5820bd8c054f8c016"},"schema_version":"1.0","source":{"id":"1912.06366","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.06366","created_at":"2026-07-05T00:42:22Z"},{"alias_kind":"arxiv_version","alias_value":"1912.06366v2","created_at":"2026-07-05T00:42:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.06366","created_at":"2026-07-05T00:42:22Z"},{"alias_kind":"pith_short_12","alias_value":"DMLOGIMKBQ5O","created_at":"2026-07-05T00:42:22Z"},{"alias_kind":"pith_short_16","alias_value":"DMLOGIMKBQ5OQ4FV","created_at":"2026-07-05T00:42:22Z"},{"alias_kind":"pith_short_8","alias_value":"DMLOGIMK","created_at":"2026-07-05T00:42:22Z"}],"graph_snapshots":[{"event_id":"sha256:9acc231946899b08c926ee111a2e5cd50cfcc0bc76e6723fffa78eb440d1b44d","target":"graph","created_at":"2026-07-05T00:42:22Z","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/1912.06366/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We establish that an optimistic variant of Q-learning applied to a fixed-horizon episodic Markov decision process with an aggregated state representation incurs regret $\\tilde{\\mathcal{O}}(\\sqrt{H^5 M K} + \\epsilon HK)$, where $H$ is the horizon, $M$ is the number of aggregate states, $K$ is the number of episodes, and $\\epsilon$ is the largest difference between any pair of optimal state-action values associated with a common aggregate state. Notably, this regret bound does not depend on the number of states or actions and indicates that asymptotic per-period regret is no greater than $\\epsil","authors_text":"Benjamin Van Roy, Shi Dong, Zhengyuan Zhou","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-13T09:10:18Z","title":"Provably Efficient Reinforcement Learning with Aggregated States"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.06366","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:e629451c0bb455581b1ac6d9fdd4aad139037c5668576c600cb836f89af8fbb2","target":"record","created_at":"2026-07-05T00:42:22Z","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":"29ac0d533a859c398531fe4b90d189a8c658021cab32d4bbe00b611e90b637c0","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-12-13T09:10:18Z","title_canon_sha256":"da8a3acef53a90a5571056e6bdbf3a6af3bcaca6642aefa5820bd8c054f8c016"},"schema_version":"1.0","source":{"id":"1912.06366","kind":"arxiv","version":2}},"canonical_sha256":"1b16e3218a0c3ae870b546787bed36eb2c5dd1220fbf82434cb057bf1b184ef3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b16e3218a0c3ae870b546787bed36eb2c5dd1220fbf82434cb057bf1b184ef3","first_computed_at":"2026-07-05T00:42:22.259055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:42:22.259055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tbrn4m674eJIXIucHpuac3socMSJpgxtqs2qNdN26QCZjP5477evbda8UNwTWef8csjSdZ1Z4UnDAVegB1mxDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:42:22.259567Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.06366","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e629451c0bb455581b1ac6d9fdd4aad139037c5668576c600cb836f89af8fbb2","sha256:9acc231946899b08c926ee111a2e5cd50cfcc0bc76e6723fffa78eb440d1b44d"],"state_sha256":"1b48b350e0c86783efa06dec4d67898a06fbed43c424624063d4f0bf7888896d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7eSsFczZDtb68WGU0OCrrlbo/yOz9YCS+DegGGbBBomVze5B8ZcmGE0iXWT2SyhMY5idJ4YGW11e/GJdWQmABA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T16:06:21.593992Z","bundle_sha256":"a6cdc0582ef5280a2333343a159bc433ccb0a12547782261b833dff2cf5e5b60"}}