{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K2F7QQUFEPPZO3ENNYHBPKOR52","short_pith_number":"pith:K2F7QQUF","schema_version":"1.0","canonical_sha256":"568bf8428523df976c8d6e0e17a9d1ee92cce72a5617387712e1cfe31110a03f","source":{"kind":"arxiv","id":"2502.18415","version":2},"attestation_state":"computed","paper":{"title":"Off-Policy Temporal Difference Learning for Perturbed Markov Decision Processes: Theoretical Insights and Extensive Simulations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Ali Forootani, Massimo Tipaldi, Mohammad Khosravi, Raffaele Iervolino","submitted_at":"2025-02-25T18:11:42Z","abstract_excerpt":"Dynamic Programming suffers from the curse of dimensionality due to large state and action spaces, a challenge further compounded by uncertainties in the environment. To mitigate these issue, we explore an off-policy based Temporal Difference Approximate Dynamic Programming approach that preserves contraction mapping when projecting the problem into a subspace of selected features, accounting for the probability distribution of the perturbed transition probability matrix. We further demonstrate how this Approximate Dynamic Programming approach can be implemented as a particular variant of the "},"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":"2502.18415","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.SY","submitted_at":"2025-02-25T18:11:42Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"03be0b09ff15e25545e757d821baf72ab7e3be070399ec266c581fbde0053893","abstract_canon_sha256":"e6dcfed22efcc65577a83fd9842f1382903e5d14e098f9d149686d5b0e7e20d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:02.828233Z","signature_b64":"r0cndv49o8/ERr7Iw/BzuWXBZauKoE5gQCWdjvZTwEF+CJgrHwxKvWTIHCG1TVRkj0rHH0f0NKiCmZoF/MeTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"568bf8428523df976c8d6e0e17a9d1ee92cce72a5617387712e1cfe31110a03f","last_reissued_at":"2026-07-05T10:24:02.827311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:02.827311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Off-Policy Temporal Difference Learning for Perturbed Markov Decision Processes: Theoretical Insights and Extensive Simulations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Ali Forootani, Massimo Tipaldi, Mohammad Khosravi, Raffaele Iervolino","submitted_at":"2025-02-25T18:11:42Z","abstract_excerpt":"Dynamic Programming suffers from the curse of dimensionality due to large state and action spaces, a challenge further compounded by uncertainties in the environment. To mitigate these issue, we explore an off-policy based Temporal Difference Approximate Dynamic Programming approach that preserves contraction mapping when projecting the problem into a subspace of selected features, accounting for the probability distribution of the perturbed transition probability matrix. We further demonstrate how this Approximate Dynamic Programming approach can be implemented as a particular variant of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18415","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.18415/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":"2502.18415","created_at":"2026-07-05T10:24:02.827437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18415v2","created_at":"2026-07-05T10:24:02.827437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18415","created_at":"2026-07-05T10:24:02.827437+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2F7QQUFEPPZ","created_at":"2026-07-05T10:24:02.827437+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2F7QQUFEPPZO3EN","created_at":"2026-07-05T10:24:02.827437+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2F7QQUF","created_at":"2026-07-05T10:24:02.827437+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/K2F7QQUFEPPZO3ENNYHBPKOR52","json":"https://pith.science/pith/K2F7QQUFEPPZO3ENNYHBPKOR52.json","graph_json":"https://pith.science/api/pith-number/K2F7QQUFEPPZO3ENNYHBPKOR52/graph.json","events_json":"https://pith.science/api/pith-number/K2F7QQUFEPPZO3ENNYHBPKOR52/events.json","paper":"https://pith.science/paper/K2F7QQUF"},"agent_actions":{"view_html":"https://pith.science/pith/K2F7QQUFEPPZO3ENNYHBPKOR52","download_json":"https://pith.science/pith/K2F7QQUFEPPZO3ENNYHBPKOR52.json","view_paper":"https://pith.science/paper/K2F7QQUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18415&json=true","fetch_graph":"https://pith.science/api/pith-number/K2F7QQUFEPPZO3ENNYHBPKOR52/graph.json","fetch_events":"https://pith.science/api/pith-number/K2F7QQUFEPPZO3ENNYHBPKOR52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2F7QQUFEPPZO3ENNYHBPKOR52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2F7QQUFEPPZO3ENNYHBPKOR52/action/storage_attestation","attest_author":"https://pith.science/pith/K2F7QQUFEPPZO3ENNYHBPKOR52/action/author_attestation","sign_citation":"https://pith.science/pith/K2F7QQUFEPPZO3ENNYHBPKOR52/action/citation_signature","submit_replication":"https://pith.science/pith/K2F7QQUFEPPZO3ENNYHBPKOR52/action/replication_record"}},"created_at":"2026-07-05T10:24:02.827437+00:00","updated_at":"2026-07-05T10:24:02.827437+00:00"}