{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4ALCDYUV6VG2VMAIB5M3MESXX7","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":"59bda942b22bd17d3272a69d688b028903ee9f6bdd8c701f725eba09ae2d881d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T02:45:28Z","title_canon_sha256":"b1f010d33335225f65dbf0ce53fdac4d873beebfd99ee7110201f3b441893c7a"},"schema_version":"1.0","source":{"id":"2508.21314","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.21314","created_at":"2026-07-05T12:03:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.21314v2","created_at":"2026-07-05T12:03:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21314","created_at":"2026-07-05T12:03:52Z"},{"alias_kind":"pith_short_12","alias_value":"4ALCDYUV6VG2","created_at":"2026-07-05T12:03:52Z"},{"alias_kind":"pith_short_16","alias_value":"4ALCDYUV6VG2VMAI","created_at":"2026-07-05T12:03:52Z"},{"alias_kind":"pith_short_8","alias_value":"4ALCDYUV","created_at":"2026-07-05T12:03:52Z"}],"graph_snapshots":[{"event_id":"sha256:70be18f9c1f440343a3e51cdc7228c8749fbcbaa5a8bd8ddacd3c7510686cab1","target":"graph","created_at":"2026-07-05T12:03:52Z","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/2508.21314/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a framework to understand the convergence of commonly used Q-learning reinforcement learning algorithms in practice. Two salient features of such algorithms are: (i)~the Q-table is recursively updated using an agent state (such as the state of a recurrent neural network) which is not a belief state or an information state and (ii)~policy regularization is often used to encourage exploration and stabilize the learning algorithm. We investigate the simplest form of such Q-learning algorithms which we call regularized agent-state-based Q-learning (RASQL) and show that it","authors_text":"Aditya Mahajan, Amit Sinha, Matthieu Geist","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T02:45:28Z","title":"Convergence of regularized agent-state-based Q-learning in POMDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21314","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":"sha256:7f84a09612c13e8e94e8e29c456a16c972c45bccac250019dbff0022753d38e5","target":"record","created_at":"2026-07-05T12:03:52Z","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":"59bda942b22bd17d3272a69d688b028903ee9f6bdd8c701f725eba09ae2d881d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T02:45:28Z","title_canon_sha256":"b1f010d33335225f65dbf0ce53fdac4d873beebfd99ee7110201f3b441893c7a"},"schema_version":"1.0","source":{"id":"2508.21314","kind":"arxiv","version":2}},"canonical_sha256":"e01621e295f54daab0080f59b61257bfdad8cdf4d77f67a5e997cc74c235b66b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e01621e295f54daab0080f59b61257bfdad8cdf4d77f67a5e997cc74c235b66b","first_computed_at":"2026-07-05T12:03:52.155553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:52.155553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P5qBw+RO+ZsEu+r9ca6h567iweIGoFUW6MMJbVIbu7FvrFnGc/UPZDoU6lOIHs951A0w8xxX8JuIwvCxXefRCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:52.156053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.21314","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f84a09612c13e8e94e8e29c456a16c972c45bccac250019dbff0022753d38e5","sha256:70be18f9c1f440343a3e51cdc7228c8749fbcbaa5a8bd8ddacd3c7510686cab1"],"state_sha256":"96b282fe0aeec42d29601a36dafbce74dee9b527c00944711cb147d3b7bb8b8d"}