{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GH2GTIUZE5US5DEEPTD6W4IZ33","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":"80b263c6c2b4c086bbac73e46ad660d87ed83422dcbbba21ec91208371f534c5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-29T16:53:00Z","title_canon_sha256":"cd6adf816622a9b54e8d83e6e85faf31c4d777f141f0f6a39f8374a8c502c733"},"schema_version":"1.0","source":{"id":"2205.01053","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.01053","created_at":"2026-07-05T04:24:25Z"},{"alias_kind":"arxiv_version","alias_value":"2205.01053v2","created_at":"2026-07-05T04:24:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01053","created_at":"2026-07-05T04:24:25Z"},{"alias_kind":"pith_short_12","alias_value":"GH2GTIUZE5US","created_at":"2026-07-05T04:24:25Z"},{"alias_kind":"pith_short_16","alias_value":"GH2GTIUZE5US5DEE","created_at":"2026-07-05T04:24:25Z"},{"alias_kind":"pith_short_8","alias_value":"GH2GTIUZ","created_at":"2026-07-05T04:24:25Z"}],"graph_snapshots":[{"event_id":"sha256:0d79d30f0adedbdb03f1861ec2cfdcaaba3980c08627388fecd02e885d3a1919","target":"graph","created_at":"2026-07-05T04:24:25Z","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/2205.01053/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Our work aims at developing reinforcement learning algorithms that do not rely on the Markov assumption. We consider the class of Non-Markov Decision Processes where histories can be abstracted into a finite set of states while preserving the dynamics. We call it a Markov abstraction since it induces a Markov Decision Process over a set of states that encode the non-Markov dynamics. This phenomenon underlies the recently introduced Regular Decision Processes (as well as POMDPs where only a finite number of belief states is reachable). In all such kinds of decision process, an agent that uses a","authors_text":"Alessandro Ronca, Gabriel Paludo Licks, Giuseppe De Giacomo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-29T16:53:00Z","title":"Markov Abstractions for PAC Reinforcement Learning in Non-Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.01053","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:e7775e5c14e5ff61bfc63f7c2cbf274108a597be885ba7df5d60e638dbaad3d0","target":"record","created_at":"2026-07-05T04:24:25Z","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":"80b263c6c2b4c086bbac73e46ad660d87ed83422dcbbba21ec91208371f534c5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-29T16:53:00Z","title_canon_sha256":"cd6adf816622a9b54e8d83e6e85faf31c4d777f141f0f6a39f8374a8c502c733"},"schema_version":"1.0","source":{"id":"2205.01053","kind":"arxiv","version":2}},"canonical_sha256":"31f469a29927692e8c847cc7eb7119deccf54ed37d9b4f86e19895b062910e2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31f469a29927692e8c847cc7eb7119deccf54ed37d9b4f86e19895b062910e2d","first_computed_at":"2026-07-05T04:24:25.881833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:25.881833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gdRWezqjz0UJ27H9ECC4mXkldaXWF2eafxlngeOqnCJ++Jxi+mE5r7Fbho+7JukUnovhn0up1Ck2vNE6ZRy0DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:25.882199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.01053","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7775e5c14e5ff61bfc63f7c2cbf274108a597be885ba7df5d60e638dbaad3d0","sha256:0d79d30f0adedbdb03f1861ec2cfdcaaba3980c08627388fecd02e885d3a1919"],"state_sha256":"994bdd15b8fbdc2cc4be61ac6e9ce7126938c1c0e98821ac7aa3c3f67d78549e"}