{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y4HIXO76SO2SULYI2LKGCKTZLZ","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":"ff9c1a2d3dd66910d084d463cd964bbffaca54b88a248a1876e2405e27204fa5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T16:10:50Z","title_canon_sha256":"b0991523154d4ceddb3eaae02a6874f509bd9e067ee967bae11b6909760db017"},"schema_version":"1.0","source":{"id":"2501.19254","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.19254","created_at":"2026-07-05T11:10:34Z"},{"alias_kind":"arxiv_version","alias_value":"2501.19254v4","created_at":"2026-07-05T11:10:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19254","created_at":"2026-07-05T11:10:34Z"},{"alias_kind":"pith_short_12","alias_value":"Y4HIXO76SO2S","created_at":"2026-07-05T11:10:34Z"},{"alias_kind":"pith_short_16","alias_value":"Y4HIXO76SO2SULYI","created_at":"2026-07-05T11:10:34Z"},{"alias_kind":"pith_short_8","alias_value":"Y4HIXO76","created_at":"2026-07-05T11:10:34Z"}],"graph_snapshots":[{"event_id":"sha256:ad25458bdb89a9b05a10d2f006ca0bc2ebc2c795555344b8325b11a9f7966476","target":"graph","created_at":"2026-07-05T11:10:34Z","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/2501.19254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"$Q$-learning is one of the most fundamental reinforcement learning algorithms. It is widely believed that $Q$-learning with linear function approximation (i.e., linear $Q$-learning) suffers from possible divergence until the recent work Meyn (2024) which establishes the ultimate almost sure boundedness of the iterates of linear $Q$-learning. Building on this success, this paper further establishes the first $L^2$ convergence rate of linear $Q$-learning iterates (to a bounded set). Similar to Meyn (2024), we do not make any modification to the original linear $Q$-learning algorithm, do not make","authors_text":"Shangtong Zhang, Xinyu Liu, Zixuan Xie","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T16:10:50Z","title":"Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19254","kind":"arxiv","version":4},"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":"sha256:67bab6111342708fc31f5c76745b378e59a9363794e8d57d91cf1b54e677e5e2","target":"record","created_at":"2026-07-05T11:10:34Z","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":"ff9c1a2d3dd66910d084d463cd964bbffaca54b88a248a1876e2405e27204fa5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T16:10:50Z","title_canon_sha256":"b0991523154d4ceddb3eaae02a6874f509bd9e067ee967bae11b6909760db017"},"schema_version":"1.0","source":{"id":"2501.19254","kind":"arxiv","version":4}},"canonical_sha256":"c70e8bbbfe93b52a2f08d2d4612a795e67230046ee447d2c1328b743f7d6ab2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c70e8bbbfe93b52a2f08d2d4612a795e67230046ee447d2c1328b743f7d6ab2a","first_computed_at":"2026-07-05T11:10:34.338262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:34.338262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vDI9LIVEzmf7rgCTn+yw5bvzJ5rTL9YSc0iENa0GYsYPuqZc7B/f+TMvOjQDJIPFhWVeRcGKjpFDKgjJA806Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:34.338746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.19254","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67bab6111342708fc31f5c76745b378e59a9363794e8d57d91cf1b54e677e5e2","sha256:ad25458bdb89a9b05a10d2f006ca0bc2ebc2c795555344b8325b11a9f7966476"],"state_sha256":"e85baf81a209bda72cf22c38954682b224488ce32aef5ac772b9f89f96b7f099"}