{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XGLQBXIGVPCNR3DORRASFODQPA","short_pith_number":"pith:XGLQBXIG","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"},"canonical_sha256":"b99700dd06abc4d8ec6e8c4122b8707836e9d663d1bcfd8023822ed4ebb21653","source":{"kind":"arxiv","id":"2411.14019","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14019","created_at":"2026-07-05T09:38:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14019v1","created_at":"2026-07-05T09:38:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14019","created_at":"2026-07-05T09:38:40Z"},{"alias_kind":"pith_short_12","alias_value":"XGLQBXIGVPCN","created_at":"2026-07-05T09:38:40Z"},{"alias_kind":"pith_short_16","alias_value":"XGLQBXIGVPCNR3DO","created_at":"2026-07-05T09:38:40Z"},{"alias_kind":"pith_short_8","alias_value":"XGLQBXIG","created_at":"2026-07-05T09:38:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XGLQBXIGVPCNR3DORRASFODQPA","target":"record","payload":{"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"},"canonical_sha256":"b99700dd06abc4d8ec6e8c4122b8707836e9d663d1bcfd8023822ed4ebb21653","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"},"source_kind":"arxiv","source_id":"2411.14019","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:38:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FIktc/TYXXfvNizYGLGFe/sz7xyQeoSlC6hCXrxBw3PUjFn/Tq7GF7Bk2m/KU8DY3/tvOLCGCG5EPdqUHZwrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:23:56.225357Z"},"content_sha256":"d830ae1b80fbc031ed1c2d37580106d9c99787517e7907c1fadc792ae8bf9204","schema_version":"1.0","event_id":"sha256:d830ae1b80fbc031ed1c2d37580106d9c99787517e7907c1fadc792ae8bf9204"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XGLQBXIGVPCNR3DORRASFODQPA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:38:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zl0tthz7C1Ehe176tIe9EWC/9+zAa7mBCY4dk7vXbvNpapfLKuHgFdFR2IbhA7P+qan9ZDCP1RWOAj5CEaAVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T02:23:56.225857Z"},"content_sha256":"b2b6d45820f7b1bf220a6744a94e5bc904eeccf2138ddc01af5100273bdf767f","schema_version":"1.0","event_id":"sha256:b2b6d45820f7b1bf220a6744a94e5bc904eeccf2138ddc01af5100273bdf767f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA/bundle.json","state_url":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XGLQBXIGVPCNR3DORRASFODQPA/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":"2026-08-13T02:23:56Z","links":{"resolver":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA","bundle":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA/bundle.json","state":"https://pith.science/pith/XGLQBXIGVPCNR3DORRASFODQPA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XGLQBXIGVPCNR3DORRASFODQPA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XGLQBXIGVPCNR3DORRASFODQPA","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":"96bb049c2c82d2b0f206f96a2954422cb922f4d6131b14fd0964bc4d5c05704a","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T11:03:07Z","title_canon_sha256":"4a1f9b21c68d0a7ac721b3bb7d2c63d4bdb1bad7dea8af22dc825622d0f33685"},"schema_version":"1.0","source":{"id":"2411.14019","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14019","created_at":"2026-07-05T09:38:40Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14019v1","created_at":"2026-07-05T09:38:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14019","created_at":"2026-07-05T09:38:40Z"},{"alias_kind":"pith_short_12","alias_value":"XGLQBXIGVPCN","created_at":"2026-07-05T09:38:40Z"},{"alias_kind":"pith_short_16","alias_value":"XGLQBXIGVPCNR3DO","created_at":"2026-07-05T09:38:40Z"},{"alias_kind":"pith_short_8","alias_value":"XGLQBXIG","created_at":"2026-07-05T09:38:40Z"}],"graph_snapshots":[{"event_id":"sha256:b2b6d45820f7b1bf220a6744a94e5bc904eeccf2138ddc01af5100273bdf767f","target":"graph","created_at":"2026-07-05T09:38:40Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.14019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Mahammad Humayoo","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T11:03:07Z","title":"Time-Scale Separation in Q-Learning: Extending TD($\\triangle$) for Action-Value Function Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14019","kind":"arxiv","version":1},"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:d830ae1b80fbc031ed1c2d37580106d9c99787517e7907c1fadc792ae8bf9204","target":"record","created_at":"2026-07-05T09:38:40Z","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":"96bb049c2c82d2b0f206f96a2954422cb922f4d6131b14fd0964bc4d5c05704a","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-21T11:03:07Z","title_canon_sha256":"4a1f9b21c68d0a7ac721b3bb7d2c63d4bdb1bad7dea8af22dc825622d0f33685"},"schema_version":"1.0","source":{"id":"2411.14019","kind":"arxiv","version":1}},"canonical_sha256":"b99700dd06abc4d8ec6e8c4122b8707836e9d663d1bcfd8023822ed4ebb21653","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b99700dd06abc4d8ec6e8c4122b8707836e9d663d1bcfd8023822ed4ebb21653","first_computed_at":"2026-07-05T09:38:40.432095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:40.432095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UMSfu40snHJ9g7Hlvzd9ohFR5MIBnOtoKdPgmBaxoDiGcVzQKHSt/kQkIyh6bjVIk/yEl1VhxM8402L/IXnmDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:40.432604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14019","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d830ae1b80fbc031ed1c2d37580106d9c99787517e7907c1fadc792ae8bf9204","sha256:b2b6d45820f7b1bf220a6744a94e5bc904eeccf2138ddc01af5100273bdf767f"],"state_sha256":"82b836d8aa4fe6596b76111881486e7585ffc2159167874ced79d2eea72048f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WgBu1dpKpAWsFllqR6Jnh4wUoo2lVBE4bZcrbO/qhCudVDon389owQ/5CGC9WEVXHW90zp+z803+jPPsJjrqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T02:23:56.230709Z","bundle_sha256":"e7b6850b73857dc1798e3062136689a2cedbb75670036d0b2b604ec5e103fa99"}}