{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EUW27DPWITAXLTWLA4N74IUNKM","short_pith_number":"pith:EUW27DPW","canonical_record":{"source":{"id":"1704.05147","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-17T23:18:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a46e3cbb5f068e9a81a4f1228c5019e83bf95c1f48c55876590773e70abfb47e","abstract_canon_sha256":"119fe33c650c383abc8a2c2ac2b9b473b2c9b5a01e6b371f1f8e179d7abd3bb8"},"schema_version":"1.0"},"canonical_sha256":"252daf8df644c175cecb071bfe228d532e3ee22c320e6ce5507532ac5366fae2","source":{"kind":"arxiv","id":"1704.05147","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.05147","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"arxiv_version","alias_value":"1704.05147v2","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.05147","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"pith_short_12","alias_value":"EUW27DPWITAX","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EUW27DPWITAXLTWL","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EUW27DPW","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EUW27DPWITAXLTWLA4N74IUNKM","target":"record","payload":{"canonical_record":{"source":{"id":"1704.05147","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-17T23:18:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a46e3cbb5f068e9a81a4f1228c5019e83bf95c1f48c55876590773e70abfb47e","abstract_canon_sha256":"119fe33c650c383abc8a2c2ac2b9b473b2c9b5a01e6b371f1f8e179d7abd3bb8"},"schema_version":"1.0"},"canonical_sha256":"252daf8df644c175cecb071bfe228d532e3ee22c320e6ce5507532ac5366fae2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:03.897242Z","signature_b64":"GVMyB02LvxDY+ezs+NbBFsrwitJkOhUiA05f7rMerQdupypY4HiR96hZimtPUN7A8MlGhYXjnCmkxUY/4nA5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"252daf8df644c175cecb071bfe228d532e3ee22c320e6ce5507532ac5366fae2","last_reissued_at":"2026-05-18T00:46:03.896879Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:03.896879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.05147","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":"2026-05-18T00:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wBNHVyKmngO7e8UCTLAtyjQPnftjz7Gxte3ETqhFhkxgZdMF6sRdCluLsNoMbDN1kLTnNQoewFLxnb6m157JCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T13:17:49.548868Z"},"content_sha256":"f9b72b55e7a536d3b82af107579e3d16f7f69be8622754a8f454d08407107a67","schema_version":"1.0","event_id":"sha256:f9b72b55e7a536d3b82af107579e3d16f7f69be8622754a8f454d08407107a67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EUW27DPWITAXLTWLA4N74IUNKM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"O$^2$TD: (Near)-Optimal Off-Policy TD Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Liu, Daoming Lyu, Saad Biaz, Wen Dong","submitted_at":"2017-04-17T23:18:48Z","abstract_excerpt":"Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions is optimal w.r.t approximating the true value function $V$. Two novel algorithms are proposed to approximate the true value function $V$. This paper makes the following contributions: (1) A batch algorithm that can help find the approximate optimal off-policy prediction of the true value function $V$. (2) A linear computational cost (per step) near-optimal algorithm that can learn from a collection o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.05147","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":"2026-05-18T00:46:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wu4PSyd5h+ynzkp7wEWOKXMuPujmJEV2fKVMqRvXicwTUYs2nR/Kxgzpscm37mTZT1WCVu06xeU5mM1rKWvRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T13:17:49.549609Z"},"content_sha256":"3f307523ef3ed04601b5101be12f9e82cebb410d82ef6c14bc70a4de935b9cce","schema_version":"1.0","event_id":"sha256:3f307523ef3ed04601b5101be12f9e82cebb410d82ef6c14bc70a4de935b9cce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EUW27DPWITAXLTWLA4N74IUNKM/bundle.json","state_url":"https://pith.science/pith/EUW27DPWITAXLTWLA4N74IUNKM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EUW27DPWITAXLTWLA4N74IUNKM/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":"2026-05-31T13:17:49Z","links":{"resolver":"https://pith.science/pith/EUW27DPWITAXLTWLA4N74IUNKM","bundle":"https://pith.science/pith/EUW27DPWITAXLTWLA4N74IUNKM/bundle.json","state":"https://pith.science/pith/EUW27DPWITAXLTWLA4N74IUNKM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EUW27DPWITAXLTWLA4N74IUNKM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EUW27DPWITAXLTWLA4N74IUNKM","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":"119fe33c650c383abc8a2c2ac2b9b473b2c9b5a01e6b371f1f8e179d7abd3bb8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-17T23:18:48Z","title_canon_sha256":"a46e3cbb5f068e9a81a4f1228c5019e83bf95c1f48c55876590773e70abfb47e"},"schema_version":"1.0","source":{"id":"1704.05147","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.05147","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"arxiv_version","alias_value":"1704.05147v2","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.05147","created_at":"2026-05-18T00:46:03Z"},{"alias_kind":"pith_short_12","alias_value":"EUW27DPWITAX","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EUW27DPWITAXLTWL","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EUW27DPW","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:3f307523ef3ed04601b5101be12f9e82cebb410d82ef6c14bc70a4de935b9cce","target":"graph","created_at":"2026-05-18T00:46:03Z","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":"Temporal difference learning and Residual Gradient methods are the most widely used temporal difference based learning algorithms; however, it has been shown that none of their objective functions is optimal w.r.t approximating the true value function $V$. Two novel algorithms are proposed to approximate the true value function $V$. This paper makes the following contributions: (1) A batch algorithm that can help find the approximate optimal off-policy prediction of the true value function $V$. (2) A linear computational cost (per step) near-optimal algorithm that can learn from a collection o","authors_text":"Bo Liu, Daoming Lyu, Saad Biaz, Wen Dong","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-17T23:18:48Z","title":"O$^2$TD: (Near)-Optimal Off-Policy TD Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.05147","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:f9b72b55e7a536d3b82af107579e3d16f7f69be8622754a8f454d08407107a67","target":"record","created_at":"2026-05-18T00:46:03Z","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":"119fe33c650c383abc8a2c2ac2b9b473b2c9b5a01e6b371f1f8e179d7abd3bb8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-17T23:18:48Z","title_canon_sha256":"a46e3cbb5f068e9a81a4f1228c5019e83bf95c1f48c55876590773e70abfb47e"},"schema_version":"1.0","source":{"id":"1704.05147","kind":"arxiv","version":2}},"canonical_sha256":"252daf8df644c175cecb071bfe228d532e3ee22c320e6ce5507532ac5366fae2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"252daf8df644c175cecb071bfe228d532e3ee22c320e6ce5507532ac5366fae2","first_computed_at":"2026-05-18T00:46:03.896879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:03.896879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GVMyB02LvxDY+ezs+NbBFsrwitJkOhUiA05f7rMerQdupypY4HiR96hZimtPUN7A8MlGhYXjnCmkxUY/4nA5Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:03.897242Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.05147","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9b72b55e7a536d3b82af107579e3d16f7f69be8622754a8f454d08407107a67","sha256:3f307523ef3ed04601b5101be12f9e82cebb410d82ef6c14bc70a4de935b9cce"],"state_sha256":"936599a9db86dcb5d921e45c9dcd7966e21fbc5126f409123e2a4ab8adfc1b81"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UZ78WdHMhF8FTKNR8sZGQX0UbQIiKLTgXBwEO6DdtjHYaqYVIiLc6URsdf6C6193UwkYTzdxaf4OLm7+MGrXDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T13:17:49.553695Z","bundle_sha256":"9019567ee4bc17d56d4671e57dc34f354639a3554b787238cfbdbd21fb739d46"}}