{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7L5EQJYRWDFDRQY4P2V2NXYMEW","short_pith_number":"pith:7L5EQJYR","canonical_record":{"source":{"id":"1909.02506","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-05T16:20:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3bb95c5281f87b8024449c01dcbd03cebfa9bde4743205fcf8698829dd2dc09c","abstract_canon_sha256":"24b38c177900bb059a79950f8fe17d271e6f0f4f26fe9ac95b44d605171514e5"},"schema_version":"1.0"},"canonical_sha256":"fafa482711b0ca38c31c7eaba6df0c25b965840d474d8ac87e13196d34863ead","source":{"kind":"arxiv","id":"1909.02506","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02506","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02506v3","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02506","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"7L5EQJYRWDFD","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"7L5EQJYRWDFDRQY4","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"7L5EQJYR","created_at":"2026-07-05T01:11:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7L5EQJYRWDFDRQY4P2V2NXYMEW","target":"record","payload":{"canonical_record":{"source":{"id":"1909.02506","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-05T16:20:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3bb95c5281f87b8024449c01dcbd03cebfa9bde4743205fcf8698829dd2dc09c","abstract_canon_sha256":"24b38c177900bb059a79950f8fe17d271e6f0f4f26fe9ac95b44d605171514e5"},"schema_version":"1.0"},"canonical_sha256":"fafa482711b0ca38c31c7eaba6df0c25b965840d474d8ac87e13196d34863ead","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:41.496393Z","signature_b64":"UOpVIAQDHbGVJVEybV3SHs6PFIowMoTP6kbJ8l5bIuFfDu67EU13dCHWLcz1DczkfKKMF0JJEHppPfZyEE/UAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fafa482711b0ca38c31c7eaba6df0c25b965840d474d8ac87e13196d34863ead","last_reissued_at":"2026-07-05T01:11:41.495821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:41.495821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.02506","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dcCJL3dXL/pYB2RnR65FyaEKhMCwuJjX4/5RCSeMRn3doGNjc2IWVORLmbCupzxVxZSstQ5GWK9tFwb1RvurBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T09:58:29.958962Z"},"content_sha256":"cbb94807d1b005264ad40eab01c94a410a38e80c71ce5c54e38b9e2e7cfc9e16","schema_version":"1.0","event_id":"sha256:cbb94807d1b005264ad40eab01c94a410a38e80c71ce5c54e38b9e2e7cfc9e16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7L5EQJYRWDFDRQY4P2V2NXYMEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"$\\sqrt{n}$-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Peng, Kefan Dong, Yining Wang, Yuan Zhou","submitted_at":"2019-09-05T16:20:41Z","abstract_excerpt":"In this paper, we consider the problem of online learning of Markov decision processes (MDPs) with very large state spaces. Under the assumptions of realizable function approximation and low Bellman ranks, we develop an online learning algorithm that learns the optimal value function while at the same time achieving very low cumulative regret during the learning process. Our learning algorithm, Adaptive Value-function Elimination (AVE), is inspired by the policy elimination algorithm proposed in (Jiang et al., 2017), known as OLIVE. One of our key technical contributions in AVE is to formulate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02506","kind":"arxiv","version":3},"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/1909.02506/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":"2026-07-05T01:11:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8drZjeg+tA0aqcPXwacmd1b2W78uAafGnVN245F0WBe59lqAdrZCQ6zG5p6gnsKPww+vQW9eU7AzvFzaM/BLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T09:58:29.959352Z"},"content_sha256":"36ea972ab79ac9cdbfe438c8681a21f65c3c63b04df8d8ccef0dac1e566744ca","schema_version":"1.0","event_id":"sha256:36ea972ab79ac9cdbfe438c8681a21f65c3c63b04df8d8ccef0dac1e566744ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7L5EQJYRWDFDRQY4P2V2NXYMEW/bundle.json","state_url":"https://pith.science/pith/7L5EQJYRWDFDRQY4P2V2NXYMEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7L5EQJYRWDFDRQY4P2V2NXYMEW/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":"2026-07-13T09:58:29Z","links":{"resolver":"https://pith.science/pith/7L5EQJYRWDFDRQY4P2V2NXYMEW","bundle":"https://pith.science/pith/7L5EQJYRWDFDRQY4P2V2NXYMEW/bundle.json","state":"https://pith.science/pith/7L5EQJYRWDFDRQY4P2V2NXYMEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7L5EQJYRWDFDRQY4P2V2NXYMEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7L5EQJYRWDFDRQY4P2V2NXYMEW","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":"24b38c177900bb059a79950f8fe17d271e6f0f4f26fe9ac95b44d605171514e5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-05T16:20:41Z","title_canon_sha256":"3bb95c5281f87b8024449c01dcbd03cebfa9bde4743205fcf8698829dd2dc09c"},"schema_version":"1.0","source":{"id":"1909.02506","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02506","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02506v3","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02506","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_12","alias_value":"7L5EQJYRWDFD","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_16","alias_value":"7L5EQJYRWDFDRQY4","created_at":"2026-07-05T01:11:41Z"},{"alias_kind":"pith_short_8","alias_value":"7L5EQJYR","created_at":"2026-07-05T01:11:41Z"}],"graph_snapshots":[{"event_id":"sha256:36ea972ab79ac9cdbfe438c8681a21f65c3c63b04df8d8ccef0dac1e566744ca","target":"graph","created_at":"2026-07-05T01:11:41Z","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/1909.02506/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we consider the problem of online learning of Markov decision processes (MDPs) with very large state spaces. Under the assumptions of realizable function approximation and low Bellman ranks, we develop an online learning algorithm that learns the optimal value function while at the same time achieving very low cumulative regret during the learning process. Our learning algorithm, Adaptive Value-function Elimination (AVE), is inspired by the policy elimination algorithm proposed in (Jiang et al., 2017), known as OLIVE. One of our key technical contributions in AVE is to formulate","authors_text":"Jian Peng, Kefan Dong, Yining Wang, Yuan Zhou","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-05T16:20:41Z","title":"$\\sqrt{n}$-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02506","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:cbb94807d1b005264ad40eab01c94a410a38e80c71ce5c54e38b9e2e7cfc9e16","target":"record","created_at":"2026-07-05T01:11:41Z","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":"24b38c177900bb059a79950f8fe17d271e6f0f4f26fe9ac95b44d605171514e5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-05T16:20:41Z","title_canon_sha256":"3bb95c5281f87b8024449c01dcbd03cebfa9bde4743205fcf8698829dd2dc09c"},"schema_version":"1.0","source":{"id":"1909.02506","kind":"arxiv","version":3}},"canonical_sha256":"fafa482711b0ca38c31c7eaba6df0c25b965840d474d8ac87e13196d34863ead","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fafa482711b0ca38c31c7eaba6df0c25b965840d474d8ac87e13196d34863ead","first_computed_at":"2026-07-05T01:11:41.495821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:41.495821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UOpVIAQDHbGVJVEybV3SHs6PFIowMoTP6kbJ8l5bIuFfDu67EU13dCHWLcz1DczkfKKMF0JJEHppPfZyEE/UAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:41.496393Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.02506","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbb94807d1b005264ad40eab01c94a410a38e80c71ce5c54e38b9e2e7cfc9e16","sha256:36ea972ab79ac9cdbfe438c8681a21f65c3c63b04df8d8ccef0dac1e566744ca"],"state_sha256":"de483db2cd531cddd259a725737e311ce4488a600139cc2134de510f2e7d7680"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odsWRFc53atB+XBV2iaMDaHnSPWZZIX3MY1y3BhgeYhZn4upHYvpBQDXpJKE3rOxWhgdAK8Z7h+HbUFWBax7BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T09:58:29.961856Z","bundle_sha256":"456fa90d1fcd6a2408d1578e6710c1220c57a3e1ae98194c263ed5f5f4e16b9a"}}