{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y247JZGQFIZ6X5RJX4ITGVRZOF","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":"8f9f1dc34a2dd97ecfe6c0e061279cd139b9f3158ba7ccbdae35af059ef0cc98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T15:59:39Z","title_canon_sha256":"9ca720906c39ce4fcdc3e8b9073ede43cd01ded6b22d5ba4409cb6772651c8d5"},"schema_version":"1.0","source":{"id":"2306.05991","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.05991","created_at":"2026-07-05T06:19:12Z"},{"alias_kind":"arxiv_version","alias_value":"2306.05991v1","created_at":"2026-07-05T06:19:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05991","created_at":"2026-07-05T06:19:12Z"},{"alias_kind":"pith_short_12","alias_value":"Y247JZGQFIZ6","created_at":"2026-07-05T06:19:12Z"},{"alias_kind":"pith_short_16","alias_value":"Y247JZGQFIZ6X5RJ","created_at":"2026-07-05T06:19:12Z"},{"alias_kind":"pith_short_8","alias_value":"Y247JZGQ","created_at":"2026-07-05T06:19:12Z"}],"graph_snapshots":[{"event_id":"sha256:ad401a662135b8f3cd9b7a03315a23425b43d48b9c081d9614e45705bf08cf46","target":"graph","created_at":"2026-07-05T06:19:12Z","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/2306.05991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In spite of the large literature on reinforcement learning (RL) algorithms for partially observable Markov decision processes (POMDPs), a complete theoretical understanding is still lacking. In a partially observable setting, the history of data available to the agent increases over time so most practical algorithms either truncate the history to a finite window or compress it using a recurrent neural network leading to an agent state that is non-Markovian. In this paper, it is shown that in spite of the lack of the Markov property, recurrent Q-learning (RQL) converges in the tabular setting. ","authors_text":"Aditya Mahajan, Amit Sinha, Erfan Seyedsalehi, Nima Akbarzadeh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T15:59:39Z","title":"Approximate information state based convergence analysis of recurrent Q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05991","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:b3a015f06421b779940cf486613ce7bcca72499deb43153e3e6e315485b4eaab","target":"record","created_at":"2026-07-05T06:19:12Z","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":"8f9f1dc34a2dd97ecfe6c0e061279cd139b9f3158ba7ccbdae35af059ef0cc98","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T15:59:39Z","title_canon_sha256":"9ca720906c39ce4fcdc3e8b9073ede43cd01ded6b22d5ba4409cb6772651c8d5"},"schema_version":"1.0","source":{"id":"2306.05991","kind":"arxiv","version":1}},"canonical_sha256":"c6b9f4e4d02a33ebf629bf11335639715699eb5e7c7add4556b79a899dc3a56f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6b9f4e4d02a33ebf629bf11335639715699eb5e7c7add4556b79a899dc3a56f","first_computed_at":"2026-07-05T06:19:12.599531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:19:12.599531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7itl/hRQpGGOAeEPlvaqSgqANyhbDVjSd+biZgqd6ais+NyaGJT9hCqfW8dcQ53gmvICdl2ywHyviF6E+Pq4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:19:12.599940Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.05991","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3a015f06421b779940cf486613ce7bcca72499deb43153e3e6e315485b4eaab","sha256:ad401a662135b8f3cd9b7a03315a23425b43d48b9c081d9614e45705bf08cf46"],"state_sha256":"82f854dd4452a0a0169ec21b6f39230ba50794fe0a21ab3b4ff7b54d92adf438"}