{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BRACNNQIGXMFCLTVB4ISOS7EMM","short_pith_number":"pith:BRACNNQI","canonical_record":{"source":{"id":"1905.06265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T16:06:30Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"fcc03765db7c3ce5ae0d7bd3ef59159556c6e995273be4c6dbf0d97e3ecaa4c0","abstract_canon_sha256":"19f6b7c89245aa485c1021726f02c2e8765b70652c7e6547468c86613852d203"},"schema_version":"1.0"},"canonical_sha256":"0c4026b60835d8512e750f11274be4630b89f1387f9fe617a9c41692ab6efd4d","source":{"kind":"arxiv","id":"1905.06265","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06265","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06265v2","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06265","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"pith_short_12","alias_value":"BRACNNQIGXMF","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BRACNNQIGXMFCLTV","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BRACNNQI","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BRACNNQIGXMFCLTVB4ISOS7EMM","target":"record","payload":{"canonical_record":{"source":{"id":"1905.06265","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T16:06:30Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"fcc03765db7c3ce5ae0d7bd3ef59159556c6e995273be4c6dbf0d97e3ecaa4c0","abstract_canon_sha256":"19f6b7c89245aa485c1021726f02c2e8765b70652c7e6547468c86613852d203"},"schema_version":"1.0"},"canonical_sha256":"0c4026b60835d8512e750f11274be4630b89f1387f9fe617a9c41692ab6efd4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:41.661064Z","signature_b64":"cDPe7CSwlfgcX3xQUnF1hX4HDdfPsAsEb99vZOSeFqFKf1k2STGSQ/rC6xHQUTQJL38UdC2FL9Iim5OefU/tDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c4026b60835d8512e750f11274be4630b89f1387f9fe617a9c41692ab6efd4d","last_reissued_at":"2026-05-17T23:42:41.660241Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:41.660241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.06265","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":"2026-05-17T23:42:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+WSx3CeDk7xFy79JZtWJ82fHQ8lZ/cQE+vy6vRnsfG8y65oBe59GF19CNd0pAfayBf8Y10cAssOb7/fcJP5jAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:48:45.960551Z"},"content_sha256":"a9399dffde315c35196905aa3a873aeb9062fa4c8d53ea3707645881c318e5a7","schema_version":"1.0","event_id":"sha256:a9399dffde315c35196905aa3a873aeb9062fa4c8d53ea3707645881c318e5a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BRACNNQIGXMFCLTVB4ISOS7EMM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic approximation with cone-contractive operators: Sharp $\\ell_\\infty$-bounds for $Q$-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Martin J. Wainwright","submitted_at":"2019-05-15T16:06:30Z","abstract_excerpt":"Motivated by the study of $Q$-learning algorithms in reinforcement learning, we study a class of stochastic approximation procedures based on operators that satisfy monotonicity and quasi-contractivity conditions with respect to an underlying cone. We prove a general sandwich relation on the iterate error at each time, and use it to derive non-asymptotic bounds on the error in terms of a cone-induced gauge norm. These results are derived within a deterministic framework, requiring no assumptions on the noise. We illustrate these general bounds in application to synchronous $Q$-learning for dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06265","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":""},"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":"2026-05-17T23:42:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M78NXl4g7rNcXR49zUIWpmAl6B0F6xKf42HcR49o15RiqYatu9WH5OK2yXH8DmaAncSFbGAOTutcw9DzOzH+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:48:45.960891Z"},"content_sha256":"c8ccf8520d2fec102c3177120e7ffa8fb4fef37afa256cb8d73d57e74a2877db","schema_version":"1.0","event_id":"sha256:c8ccf8520d2fec102c3177120e7ffa8fb4fef37afa256cb8d73d57e74a2877db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BRACNNQIGXMFCLTVB4ISOS7EMM/bundle.json","state_url":"https://pith.science/pith/BRACNNQIGXMFCLTVB4ISOS7EMM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BRACNNQIGXMFCLTVB4ISOS7EMM/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":"2026-06-01T21:48:45Z","links":{"resolver":"https://pith.science/pith/BRACNNQIGXMFCLTVB4ISOS7EMM","bundle":"https://pith.science/pith/BRACNNQIGXMFCLTVB4ISOS7EMM/bundle.json","state":"https://pith.science/pith/BRACNNQIGXMFCLTVB4ISOS7EMM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BRACNNQIGXMFCLTVB4ISOS7EMM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BRACNNQIGXMFCLTVB4ISOS7EMM","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":"19f6b7c89245aa485c1021726f02c2e8765b70652c7e6547468c86613852d203","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T16:06:30Z","title_canon_sha256":"fcc03765db7c3ce5ae0d7bd3ef59159556c6e995273be4c6dbf0d97e3ecaa4c0"},"schema_version":"1.0","source":{"id":"1905.06265","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06265","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06265v2","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06265","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"pith_short_12","alias_value":"BRACNNQIGXMF","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BRACNNQIGXMFCLTV","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BRACNNQI","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:c8ccf8520d2fec102c3177120e7ffa8fb4fef37afa256cb8d73d57e74a2877db","target":"graph","created_at":"2026-05-17T23:42:41Z","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"},"paper":{"abstract_excerpt":"Motivated by the study of $Q$-learning algorithms in reinforcement learning, we study a class of stochastic approximation procedures based on operators that satisfy monotonicity and quasi-contractivity conditions with respect to an underlying cone. We prove a general sandwich relation on the iterate error at each time, and use it to derive non-asymptotic bounds on the error in terms of a cone-induced gauge norm. These results are derived within a deterministic framework, requiring no assumptions on the noise. We illustrate these general bounds in application to synchronous $Q$-learning for dis","authors_text":"Martin J. Wainwright","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T16:06:30Z","title":"Stochastic approximation with cone-contractive operators: Sharp $\\ell_\\infty$-bounds for $Q$-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06265","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:a9399dffde315c35196905aa3a873aeb9062fa4c8d53ea3707645881c318e5a7","target":"record","created_at":"2026-05-17T23:42:41Z","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":"19f6b7c89245aa485c1021726f02c2e8765b70652c7e6547468c86613852d203","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T16:06:30Z","title_canon_sha256":"fcc03765db7c3ce5ae0d7bd3ef59159556c6e995273be4c6dbf0d97e3ecaa4c0"},"schema_version":"1.0","source":{"id":"1905.06265","kind":"arxiv","version":2}},"canonical_sha256":"0c4026b60835d8512e750f11274be4630b89f1387f9fe617a9c41692ab6efd4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c4026b60835d8512e750f11274be4630b89f1387f9fe617a9c41692ab6efd4d","first_computed_at":"2026-05-17T23:42:41.660241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:41.660241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cDPe7CSwlfgcX3xQUnF1hX4HDdfPsAsEb99vZOSeFqFKf1k2STGSQ/rC6xHQUTQJL38UdC2FL9Iim5OefU/tDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:41.661064Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.06265","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9399dffde315c35196905aa3a873aeb9062fa4c8d53ea3707645881c318e5a7","sha256:c8ccf8520d2fec102c3177120e7ffa8fb4fef37afa256cb8d73d57e74a2877db"],"state_sha256":"1ad692c1b956aa7c19c7f749cb884262427c102ee33b860e7067b1e8f0518903"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1psTNBOH1Qk1jaFHzq1jnEJ8bMyqCt78BFW/7ZvqCoBjgRLOsKyiapuT1jGr3o1I0iX1vocU1dygPiWz+NHDDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T21:48:45.962808Z","bundle_sha256":"4001d0e56760937efff9c9e3a8aab33ba0ff9a5569a9334db95a5fd4e1b5453b"}}