{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:IIZETBRBLNQ2URJISP2RNCZLWV","short_pith_number":"pith:IIZETBRB","schema_version":"1.0","canonical_sha256":"42324986215b61aa452893f5168b2bb5676a5902a391af78810adab971f13828","source":{"kind":"arxiv","id":"1905.07237","version":1},"attestation_state":"computed","paper":{"title":"TBQ($\\sigma$): Improving Efficiency of Trace Utilization for Off-Policy Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Pan, Longbing Cao, Longxiang Shi, Long Yang, Shijian Li","submitted_at":"2019-05-17T14:36:48Z","abstract_excerpt":"Off-policy reinforcement learning with eligibility traces is challenging because of the discrepancy between target policy and behavior policy. One common approach is to measure the difference between two policies in a probabilistic way, such as importance sampling and tree-backup. However, existing off-policy learning methods based on probabilistic policy measurement are inefficient when utilizing traces under a greedy target policy, which is ineffective for control problems. The traces are cut immediately when a non-greedy action is taken, which may lose the advantage of eligibility traces an"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.07237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-17T14:36:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e583dc6fba3db360b71419ab1ffac8a5982c17f0f62a708c434e2efae9b69957","abstract_canon_sha256":"9cec2b4c8231d2d2c4274aec1ffb4e9857ea63f2932537416d991821e828ebb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:56.085947Z","signature_b64":"DcLTu00d4YSePKj8194yKV3elspGyWdmMsimq22AVF6IPoLTw9tFRC81gHRc/PBEjA34YoDb/jM1MPRbz5QDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42324986215b61aa452893f5168b2bb5676a5902a391af78810adab971f13828","last_reissued_at":"2026-05-17T23:45:56.085399Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:56.085399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TBQ($\\sigma$): Improving Efficiency of Trace Utilization for Off-Policy Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Pan, Longbing Cao, Longxiang Shi, Long Yang, Shijian Li","submitted_at":"2019-05-17T14:36:48Z","abstract_excerpt":"Off-policy reinforcement learning with eligibility traces is challenging because of the discrepancy between target policy and behavior policy. One common approach is to measure the difference between two policies in a probabilistic way, such as importance sampling and tree-backup. However, existing off-policy learning methods based on probabilistic policy measurement are inefficient when utilizing traces under a greedy target policy, which is ineffective for control problems. The traces are cut immediately when a non-greedy action is taken, which may lose the advantage of eligibility traces an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07237","kind":"arxiv","version":1},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.07237","created_at":"2026-05-17T23:45:56.085473+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.07237v1","created_at":"2026-05-17T23:45:56.085473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07237","created_at":"2026-05-17T23:45:56.085473+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIZETBRBLNQ2","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIZETBRBLNQ2URJI","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIZETBRB","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11138","citing_title":"Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV","json":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV.json","graph_json":"https://pith.science/api/pith-number/IIZETBRBLNQ2URJISP2RNCZLWV/graph.json","events_json":"https://pith.science/api/pith-number/IIZETBRBLNQ2URJISP2RNCZLWV/events.json","paper":"https://pith.science/paper/IIZETBRB"},"agent_actions":{"view_html":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV","download_json":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV.json","view_paper":"https://pith.science/paper/IIZETBRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.07237&json=true","fetch_graph":"https://pith.science/api/pith-number/IIZETBRBLNQ2URJISP2RNCZLWV/graph.json","fetch_events":"https://pith.science/api/pith-number/IIZETBRBLNQ2URJISP2RNCZLWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV/action/storage_attestation","attest_author":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV/action/author_attestation","sign_citation":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV/action/citation_signature","submit_replication":"https://pith.science/pith/IIZETBRBLNQ2URJISP2RNCZLWV/action/replication_record"}},"created_at":"2026-05-17T23:45:56.085473+00:00","updated_at":"2026-05-17T23:45:56.085473+00:00"}