{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VS2VPTP5FSTSTFMCINZVEJE5XD","short_pith_number":"pith:VS2VPTP5","schema_version":"1.0","canonical_sha256":"acb557cdfd2ca7299582437352249db8c192494a88583a4a53e63b2eeae763b6","source":{"kind":"arxiv","id":"2211.03011","version":1},"attestation_state":"computed","paper":{"title":"On learning history based policies for controlling Markov decision processes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Mahajan, Doina Precup, Gandharv Patil","submitted_at":"2022-11-06T02:47:55Z","abstract_excerpt":"Reinforcementlearning(RL)folkloresuggeststhathistory-basedfunctionapproximationmethods,suchas recurrent neural nets or history-based state abstraction, perform better than their memory-less counterparts, due to the fact that function approximation in Markov decision processes (MDP) can be viewed as inducing a Partially observable MDP. However, there has been little formal analysis of such history-based algorithms, as most existing frameworks focus exclusively on memory-less features. In this paper, we introduce a theoretical framework for studying the behaviour of RL algorithms that learn to c"},"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":"2211.03011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-06T02:47:55Z","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"ff4f8dd62013feccb1836c009327bf16028c917b646decf1e27969a8d4e56201","abstract_canon_sha256":"c509ef1824e33bbf9c5dd4a553223030b4404f92a2414566d0e884c7192e3de1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:43.428505Z","signature_b64":"HfZltmaohklfmIPS7r99KXPhPTvJyRZfS9QClu8A4YfGcbQzCUakZXXq2y+cv5I29+nAKoOqYR8bJj7YgZz1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acb557cdfd2ca7299582437352249db8c192494a88583a4a53e63b2eeae763b6","last_reissued_at":"2026-07-05T05:13:43.428021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:43.428021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On learning history based policies for controlling Markov decision processes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Mahajan, Doina Precup, Gandharv Patil","submitted_at":"2022-11-06T02:47:55Z","abstract_excerpt":"Reinforcementlearning(RL)folkloresuggeststhathistory-basedfunctionapproximationmethods,suchas recurrent neural nets or history-based state abstraction, perform better than their memory-less counterparts, due to the fact that function approximation in Markov decision processes (MDP) can be viewed as inducing a Partially observable MDP. However, there has been little formal analysis of such history-based algorithms, as most existing frameworks focus exclusively on memory-less features. In this paper, we introduce a theoretical framework for studying the behaviour of RL algorithms that learn to c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03011","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/2211.03011/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":"2211.03011","created_at":"2026-07-05T05:13:43.428080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.03011v1","created_at":"2026-07-05T05:13:43.428080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03011","created_at":"2026-07-05T05:13:43.428080+00:00"},{"alias_kind":"pith_short_12","alias_value":"VS2VPTP5FSTS","created_at":"2026-07-05T05:13:43.428080+00:00"},{"alias_kind":"pith_short_16","alias_value":"VS2VPTP5FSTSTFMC","created_at":"2026-07-05T05:13:43.428080+00:00"},{"alias_kind":"pith_short_8","alias_value":"VS2VPTP5","created_at":"2026-07-05T05:13:43.428080+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/VS2VPTP5FSTSTFMCINZVEJE5XD","json":"https://pith.science/pith/VS2VPTP5FSTSTFMCINZVEJE5XD.json","graph_json":"https://pith.science/api/pith-number/VS2VPTP5FSTSTFMCINZVEJE5XD/graph.json","events_json":"https://pith.science/api/pith-number/VS2VPTP5FSTSTFMCINZVEJE5XD/events.json","paper":"https://pith.science/paper/VS2VPTP5"},"agent_actions":{"view_html":"https://pith.science/pith/VS2VPTP5FSTSTFMCINZVEJE5XD","download_json":"https://pith.science/pith/VS2VPTP5FSTSTFMCINZVEJE5XD.json","view_paper":"https://pith.science/paper/VS2VPTP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.03011&json=true","fetch_graph":"https://pith.science/api/pith-number/VS2VPTP5FSTSTFMCINZVEJE5XD/graph.json","fetch_events":"https://pith.science/api/pith-number/VS2VPTP5FSTSTFMCINZVEJE5XD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VS2VPTP5FSTSTFMCINZVEJE5XD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VS2VPTP5FSTSTFMCINZVEJE5XD/action/storage_attestation","attest_author":"https://pith.science/pith/VS2VPTP5FSTSTFMCINZVEJE5XD/action/author_attestation","sign_citation":"https://pith.science/pith/VS2VPTP5FSTSTFMCINZVEJE5XD/action/citation_signature","submit_replication":"https://pith.science/pith/VS2VPTP5FSTSTFMCINZVEJE5XD/action/replication_record"}},"created_at":"2026-07-05T05:13:43.428080+00:00","updated_at":"2026-07-05T05:13:43.428080+00:00"}