{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PK6C454PO57HETKQR3XXYU7URX","short_pith_number":"pith:PK6C454P","canonical_record":{"source":{"id":"1712.09652","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-27T18:43:21Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"03fb8bd3ad508e16624c09a39c5244c3c5411c038262752d3cf44d32fe1b7e67","abstract_canon_sha256":"a1e6c9318d1349995ffc2c52a68cff52679932dac6da6d03a1feeea17a7d6a6b"},"schema_version":"1.0"},"canonical_sha256":"7abc2e778f777e724d508eef7c53f48dde9f234d57efc0b9cdc1765107fe1197","source":{"kind":"arxiv","id":"1712.09652","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.09652","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"1712.09652v2","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09652","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"PK6C454PO57H","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PK6C454PO57HETKQ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PK6C454P","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PK6C454PO57HETKQR3XXYU7URX","target":"record","payload":{"canonical_record":{"source":{"id":"1712.09652","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-27T18:43:21Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"03fb8bd3ad508e16624c09a39c5244c3c5411c038262752d3cf44d32fe1b7e67","abstract_canon_sha256":"a1e6c9318d1349995ffc2c52a68cff52679932dac6da6d03a1feeea17a7d6a6b"},"schema_version":"1.0"},"canonical_sha256":"7abc2e778f777e724d508eef7c53f48dde9f234d57efc0b9cdc1765107fe1197","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:53.210868Z","signature_b64":"kaRV4Sv/efvnuWPh4ixQ/+Ro5a6DtludjqKiIUINiPRnxJ21eepLlxkiwT/oG0314g3FwQ4cJsQHMaJcaMDfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7abc2e778f777e724d508eef7c53f48dde9f234d57efc0b9cdc1765107fe1197","last_reissued_at":"2026-05-18T00:19:53.210185Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:53.210185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.09652","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":"2026-05-18T00:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QsHW3Mt3Wqq49XzBPTOw4hUga24cKGGwRzifhxmmZJjn6h8D2A1AIAC3fBlnhP7e2Jby888qnT8P8UdUvWSwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T03:16:26.164169Z"},"content_sha256":"bf6fbd3caaa9f0ed3de428e0bd5277d2313735ebf9c310a6543fa737af109029","schema_version":"1.0","event_id":"sha256:bf6fbd3caaa9f0ed3de428e0bd5277d2313735ebf9c310a6543fa737af109029"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PK6C454PO57HETKQR3XXYU7URX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Convergence of some Gradient-based Temporal-Differences Algorithms for Off-Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Huizhen Yu","submitted_at":"2017-12-27T18:43:21Z","abstract_excerpt":"We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several gradient-based TD algorithms with linear function approximation. The algorithms we analyze include: (i) two basic forms of two-time-scale gradient-based TD algorithms, which we call GTD and which minimize the mean squared projected Bellman error using stochastic gradient-descent; (ii) their \"robustified\" biased variants; (iii) their mirror-descent versions which combi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09652","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":"2026-05-18T00:19:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QQ4IEtlblm9w19U4tpczwEBFcv+Ez7ky9FdDKsp+j9wqAgN/xPY060UpmGX1WBeapG/EzqqVP1tyNyjKWVDlBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T03:16:26.164537Z"},"content_sha256":"4450b77ea57749b0d2f98067f5d9715a8bc81422913624148439e7d21e37f596","schema_version":"1.0","event_id":"sha256:4450b77ea57749b0d2f98067f5d9715a8bc81422913624148439e7d21e37f596"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX/bundle.json","state_url":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PK6C454PO57HETKQR3XXYU7URX/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":"2026-06-30T03:16:26Z","links":{"resolver":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX","bundle":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX/bundle.json","state":"https://pith.science/pith/PK6C454PO57HETKQR3XXYU7URX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PK6C454PO57HETKQR3XXYU7URX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PK6C454PO57HETKQR3XXYU7URX","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":"a1e6c9318d1349995ffc2c52a68cff52679932dac6da6d03a1feeea17a7d6a6b","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-27T18:43:21Z","title_canon_sha256":"03fb8bd3ad508e16624c09a39c5244c3c5411c038262752d3cf44d32fe1b7e67"},"schema_version":"1.0","source":{"id":"1712.09652","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.09652","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"arxiv_version","alias_value":"1712.09652v2","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09652","created_at":"2026-05-18T00:19:53Z"},{"alias_kind":"pith_short_12","alias_value":"PK6C454PO57H","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PK6C454PO57HETKQ","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PK6C454P","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:4450b77ea57749b0d2f98067f5d9715a8bc81422913624148439e7d21e37f596","target":"graph","created_at":"2026-05-18T00:19:53Z","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 consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several gradient-based TD algorithms with linear function approximation. The algorithms we analyze include: (i) two basic forms of two-time-scale gradient-based TD algorithms, which we call GTD and which minimize the mean squared projected Bellman error using stochastic gradient-descent; (ii) their \"robustified\" biased variants; (iii) their mirror-descent versions which combi","authors_text":"Huizhen Yu","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-27T18:43:21Z","title":"On Convergence of some Gradient-based Temporal-Differences Algorithms for Off-Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09652","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:bf6fbd3caaa9f0ed3de428e0bd5277d2313735ebf9c310a6543fa737af109029","target":"record","created_at":"2026-05-18T00:19:53Z","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":"a1e6c9318d1349995ffc2c52a68cff52679932dac6da6d03a1feeea17a7d6a6b","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-27T18:43:21Z","title_canon_sha256":"03fb8bd3ad508e16624c09a39c5244c3c5411c038262752d3cf44d32fe1b7e67"},"schema_version":"1.0","source":{"id":"1712.09652","kind":"arxiv","version":2}},"canonical_sha256":"7abc2e778f777e724d508eef7c53f48dde9f234d57efc0b9cdc1765107fe1197","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7abc2e778f777e724d508eef7c53f48dde9f234d57efc0b9cdc1765107fe1197","first_computed_at":"2026-05-18T00:19:53.210185Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:53.210185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kaRV4Sv/efvnuWPh4ixQ/+Ro5a6DtludjqKiIUINiPRnxJ21eepLlxkiwT/oG0314g3FwQ4cJsQHMaJcaMDfCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:53.210868Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.09652","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf6fbd3caaa9f0ed3de428e0bd5277d2313735ebf9c310a6543fa737af109029","sha256:4450b77ea57749b0d2f98067f5d9715a8bc81422913624148439e7d21e37f596"],"state_sha256":"0d1f4cf7408a039def9cca29fec2dc754928d3774ea3b1c5709ee75d00030655"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DvtdOvBB2p7n8IXcjeXfBmdZN1FU80fDZ0b99bYydxqqw6ICxKp9CQUI57Uf0RrHNWFNyYEF40rGwP4bh0IlDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T03:16:26.166884Z","bundle_sha256":"0f96f8f6b773ff2fda7cfef47365a3e5e4fbe71ed44fb6d745d7fbae2aecff95"}}