{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q4BITHB6VN6ZJURZTKGROYPMNN","short_pith_number":"pith:Q4BITHB6","schema_version":"1.0","canonical_sha256":"8702899c3eab7d94d2399a8d1761ec6b61795030d59e9c9fe75f9ab30f0e05f9","source":{"kind":"arxiv","id":"2412.12700","version":1},"attestation_state":"computed","paper":{"title":"ParMod: A Parallel and Modular Framework for Learning Non-Markovian Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Yu, Cong Tian, Ruixuan Miao, Xu Lu, Zhenhua Duan","submitted_at":"2024-12-17T09:16:53Z","abstract_excerpt":"The commonly used Reinforcement Learning (RL) model, MDPs (Markov Decision Processes), has a basic premise that rewards depend on the current state and action only. However, many real-world tasks are non-Markovian, which has long-term memory and dependency. The reward sparseness problem is further amplified in non-Markovian scenarios. Hence learning a non-Markovian task (NMT) is inherently more difficult than learning a Markovian one. In this paper, we propose a novel \\textbf{Par}allel and \\textbf{Mod}ular RL framework, ParMod, specifically for learning NMTs specified by temporal logic. With t"},"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":"2412.12700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T09:16:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cd31b8ba8e0773d0e5fc9ae337f3ed2c7b69033533543747a0249cb5691cab7a","abstract_canon_sha256":"99d25c42793650b5d09b7c81213093afeef16ab2cb77de82d67d8d7500ec9ebd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:19.400034Z","signature_b64":"OM4vlaNkldwkZHmHjcJYMbCsnIPBY0owbyTqRIJnrPm81/us+z3jyegHbCvqs9qlyUILZ2U+AkeMeNCuKt8BDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8702899c3eab7d94d2399a8d1761ec6b61795030d59e9c9fe75f9ab30f0e05f9","last_reissued_at":"2026-07-05T09:50:19.399631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:19.399631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParMod: A Parallel and Modular Framework for Learning Non-Markovian Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Yu, Cong Tian, Ruixuan Miao, Xu Lu, Zhenhua Duan","submitted_at":"2024-12-17T09:16:53Z","abstract_excerpt":"The commonly used Reinforcement Learning (RL) model, MDPs (Markov Decision Processes), has a basic premise that rewards depend on the current state and action only. However, many real-world tasks are non-Markovian, which has long-term memory and dependency. The reward sparseness problem is further amplified in non-Markovian scenarios. Hence learning a non-Markovian task (NMT) is inherently more difficult than learning a Markovian one. In this paper, we propose a novel \\textbf{Par}allel and \\textbf{Mod}ular RL framework, ParMod, specifically for learning NMTs specified by temporal logic. With t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12700","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/2412.12700/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":"2412.12700","created_at":"2026-07-05T09:50:19.399687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12700v1","created_at":"2026-07-05T09:50:19.399687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12700","created_at":"2026-07-05T09:50:19.399687+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4BITHB6VN6Z","created_at":"2026-07-05T09:50:19.399687+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4BITHB6VN6ZJURZ","created_at":"2026-07-05T09:50:19.399687+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4BITHB6","created_at":"2026-07-05T09:50:19.399687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN","json":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN.json","graph_json":"https://pith.science/api/pith-number/Q4BITHB6VN6ZJURZTKGROYPMNN/graph.json","events_json":"https://pith.science/api/pith-number/Q4BITHB6VN6ZJURZTKGROYPMNN/events.json","paper":"https://pith.science/paper/Q4BITHB6"},"agent_actions":{"view_html":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN","download_json":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN.json","view_paper":"https://pith.science/paper/Q4BITHB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12700&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4BITHB6VN6ZJURZTKGROYPMNN/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4BITHB6VN6ZJURZTKGROYPMNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN/action/storage_attestation","attest_author":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN/action/author_attestation","sign_citation":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN/action/citation_signature","submit_replication":"https://pith.science/pith/Q4BITHB6VN6ZJURZTKGROYPMNN/action/replication_record"}},"created_at":"2026-07-05T09:50:19.399687+00:00","updated_at":"2026-07-05T09:50:19.399687+00:00"}