{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K2F7QQUFEPPZO3ENNYHBPKOR52","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":"e6dcfed22efcc65577a83fd9842f1382903e5d14e098f9d149686d5b0e7e20d7","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.SY","submitted_at":"2025-02-25T18:11:42Z","title_canon_sha256":"03be0b09ff15e25545e757d821baf72ab7e3be070399ec266c581fbde0053893"},"schema_version":"1.0","source":{"id":"2502.18415","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18415","created_at":"2026-07-05T10:24:02Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18415v2","created_at":"2026-07-05T10:24:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18415","created_at":"2026-07-05T10:24:02Z"},{"alias_kind":"pith_short_12","alias_value":"K2F7QQUFEPPZ","created_at":"2026-07-05T10:24:02Z"},{"alias_kind":"pith_short_16","alias_value":"K2F7QQUFEPPZO3EN","created_at":"2026-07-05T10:24:02Z"},{"alias_kind":"pith_short_8","alias_value":"K2F7QQUF","created_at":"2026-07-05T10:24:02Z"}],"graph_snapshots":[{"event_id":"sha256:ffa562ca11ec1f6853133a0527493c175d901a2dd987cf63330a5d1d8a314407","target":"graph","created_at":"2026-07-05T10:24:02Z","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/2502.18415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Ali Forootani, Massimo Tipaldi, Mohammad Khosravi, Raffaele Iervolino","cross_cats":["cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.SY","submitted_at":"2025-02-25T18:11:42Z","title":"Off-Policy Temporal Difference Learning for Perturbed Markov Decision Processes: Theoretical Insights and Extensive Simulations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18415","kind":"arxiv","version":2},"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:faab4fa2c6a59c313f4a1f3a5e41aa58032442d116cd9636e338b953664c49cd","target":"record","created_at":"2026-07-05T10:24:02Z","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":"e6dcfed22efcc65577a83fd9842f1382903e5d14e098f9d149686d5b0e7e20d7","cross_cats_sorted":["cs.SY"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.SY","submitted_at":"2025-02-25T18:11:42Z","title_canon_sha256":"03be0b09ff15e25545e757d821baf72ab7e3be070399ec266c581fbde0053893"},"schema_version":"1.0","source":{"id":"2502.18415","kind":"arxiv","version":2}},"canonical_sha256":"568bf8428523df976c8d6e0e17a9d1ee92cce72a5617387712e1cfe31110a03f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"568bf8428523df976c8d6e0e17a9d1ee92cce72a5617387712e1cfe31110a03f","first_computed_at":"2026-07-05T10:24:02.827311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:24:02.827311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r0cndv49o8/ERr7Iw/BzuWXBZauKoE5gQCWdjvZTwEF+CJgrHwxKvWTIHCG1TVRkj0rHH0f0NKiCmZoF/MeTAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:24:02.828233Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18415","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:faab4fa2c6a59c313f4a1f3a5e41aa58032442d116cd9636e338b953664c49cd","sha256:ffa562ca11ec1f6853133a0527493c175d901a2dd987cf63330a5d1d8a314407"],"state_sha256":"def08928d0928dc1dbb3d254270285d4589b824391c44c4902369a2b2fa860c8"}