{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VS2VPTP5FSTSTFMCINZVEJE5XD","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":"c509ef1824e33bbf9c5dd4a553223030b4404f92a2414566d0e884c7192e3de1","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-06T02:47:55Z","title_canon_sha256":"ff4f8dd62013feccb1836c009327bf16028c917b646decf1e27969a8d4e56201"},"schema_version":"1.0","source":{"id":"2211.03011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.03011","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"arxiv_version","alias_value":"2211.03011v1","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03011","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_12","alias_value":"VS2VPTP5FSTS","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_16","alias_value":"VS2VPTP5FSTSTFMC","created_at":"2026-07-05T05:13:43Z"},{"alias_kind":"pith_short_8","alias_value":"VS2VPTP5","created_at":"2026-07-05T05:13:43Z"}],"graph_snapshots":[{"event_id":"sha256:a4b594e382beb047780742ea067733115298e6a9d115708e3b7c75b7556ba288","target":"graph","created_at":"2026-07-05T05:13:43Z","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/2211.03011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aditya Mahajan, Doina Precup, Gandharv Patil","cross_cats":["cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-06T02:47:55Z","title":"On learning history based policies for controlling Markov decision processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03011","kind":"arxiv","version":1},"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:afb3f8cd38145563382374896ffca75d7d2b6c59f57e8e320b6f634b5b6e69f7","target":"record","created_at":"2026-07-05T05:13:43Z","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":"c509ef1824e33bbf9c5dd4a553223030b4404f92a2414566d0e884c7192e3de1","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-06T02:47:55Z","title_canon_sha256":"ff4f8dd62013feccb1836c009327bf16028c917b646decf1e27969a8d4e56201"},"schema_version":"1.0","source":{"id":"2211.03011","kind":"arxiv","version":1}},"canonical_sha256":"acb557cdfd2ca7299582437352249db8c192494a88583a4a53e63b2eeae763b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acb557cdfd2ca7299582437352249db8c192494a88583a4a53e63b2eeae763b6","first_computed_at":"2026-07-05T05:13:43.428021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:43.428021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HfZltmaohklfmIPS7r99KXPhPTvJyRZfS9QClu8A4YfGcbQzCUakZXXq2y+cv5I29+nAKoOqYR8bJj7YgZz1BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:43.428505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.03011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afb3f8cd38145563382374896ffca75d7d2b6c59f57e8e320b6f634b5b6e69f7","sha256:a4b594e382beb047780742ea067733115298e6a9d115708e3b7c75b7556ba288"],"state_sha256":"dfdd8dca3bbdc47d4b0a3a3079e94b9527245fab0dbf04bb54c765527bdad80b"}