{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XGLQBXIGVPCNR3DORRASFODQPA","short_pith_number":"pith:XGLQBXIG","schema_version":"1.0","canonical_sha256":"b99700dd06abc4d8ec6e8c4122b8707836e9d663d1bcfd8023822ed4ebb21653","source":{"kind":"arxiv","id":"2411.14019","version":1},"attestation_state":"computed","paper":{"title":"Time-Scale Separation in Q-Learning: Extending TD($\\triangle$) for Action-Value Function Decomposition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mahammad Humayoo","submitted_at":"2024-11-21T11:03:07Z","abstract_excerpt":"Q-Learning is a fundamental off-policy reinforcement learning (RL) algorithm that has the objective of approximating action-value functions in order to learn optimal policies. Nonetheless, it has difficulties in reconciling bias with variance, particularly in the context of long-term rewards. This paper introduces Q($\\Delta$)-Learning, an extension of TD($\\Delta$) for the Q-Learning framework. TD($\\Delta$) facilitates efficient learning over several time scales by breaking the Q($\\Delta$)-function into distinct discount factors. This approach offers improved learning stability and scalability,"},"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":"2411.14019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T11:03:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a1f9b21c68d0a7ac721b3bb7d2c63d4bdb1bad7dea8af22dc825622d0f33685","abstract_canon_sha256":"96bb049c2c82d2b0f206f96a2954422cb922f4d6131b14fd0964bc4d5c05704a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:40.432604Z","signature_b64":"UMSfu40snHJ9g7Hlvzd9ohFR5MIBnOtoKdPgmBaxoDiGcVzQKHSt/kQkIyh6bjVIk/yEl1VhxM8402L/IXnmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b99700dd06abc4d8ec6e8c4122b8707836e9d663d1bcfd8023822ed4ebb21653","last_reissued_at":"2026-07-05T09:38:40.432095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:40.432095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Time-Scale Separation in Q-Learning: Extending TD($\\triangle$) for Action-Value Function Decomposition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mahammad Humayoo","submitted_at":"2024-11-21T11:03:07Z","abstract_excerpt":"Q-Learning is a fundamental off-policy reinforcement learning (RL) algorithm that has the objective of approximating action-value functions in order to learn optimal policies. Nonetheless, it has difficulties in reconciling bias with variance, particularly in the context of long-term rewards. This paper introduces Q($\\Delta$)-Learning, an extension of TD($\\Delta$) for the Q-Learning framework. TD($\\Delta$) facilitates efficient learning over several time scales by breaking the Q($\\Delta$)-function into distinct discount factors. This approach offers improved learning stability and scalability,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14019","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.14019/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.14019","created_at":"2026-07-05T09:38:40.432161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14019v1","created_at":"2026-07-05T09:38:40.432161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14019","created_at":"2026-07-05T09:38:40.432161+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGLQBXIGVPCN","created_at":"2026-07-05T09:38:40.432161+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGLQBXIGVPCNR3DO","created_at":"2026-07-05T09:38:40.432161+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGLQBXIG","created_at":"2026-07-05T09:38:40.432161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14019","citing_title":"Time-Scale Separation in Q-Learning: Extending TD($\\triangle$) for Action-Value Function Decomposition","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA","json":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA.json","graph_json":"https://pith.science/api/pith-number/XGLQBXIGVPCNR3DORRASFODQPA/graph.json","events_json":"https://pith.science/api/pith-number/XGLQBXIGVPCNR3DORRASFODQPA/events.json","paper":"https://pith.science/paper/XGLQBXIG"},"agent_actions":{"view_html":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA","download_json":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA.json","view_paper":"https://pith.science/paper/XGLQBXIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14019&json=true","fetch_graph":"https://pith.science/api/pith-number/XGLQBXIGVPCNR3DORRASFODQPA/graph.json","fetch_events":"https://pith.science/api/pith-number/XGLQBXIGVPCNR3DORRASFODQPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA/action/storage_attestation","attest_author":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA/action/author_attestation","sign_citation":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA/action/citation_signature","submit_replication":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA/action/replication_record"}},"created_at":"2026-07-05T09:38:40.432161+00:00","updated_at":"2026-07-05T09:38:40.432161+00:00"}