{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KBJQK55SJKN4ZCXO63WO7UU547","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":"ae4f5ba6600c233553d5ecf788cf50835e6f58f8517ea8b1528d461ce56672d5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-25T07:59:20Z","title_canon_sha256":"db82fbf5469a91f12a3ab9fb870821c8907808389739d58a1adeef89039065dd"},"schema_version":"1.0","source":{"id":"2008.10870","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.10870","created_at":"2026-07-05T02:30:59Z"},{"alias_kind":"arxiv_version","alias_value":"2008.10870v2","created_at":"2026-07-05T02:30:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.10870","created_at":"2026-07-05T02:30:59Z"},{"alias_kind":"pith_short_12","alias_value":"KBJQK55SJKN4","created_at":"2026-07-05T02:30:59Z"},{"alias_kind":"pith_short_16","alias_value":"KBJQK55SJKN4ZCXO","created_at":"2026-07-05T02:30:59Z"},{"alias_kind":"pith_short_8","alias_value":"KBJQK55S","created_at":"2026-07-05T02:30:59Z"}],"graph_snapshots":[{"event_id":"sha256:2effd9b55890314f911ac09c37f029a5cb6e775169d5b6d3cebfd63a560f5d1d","target":"graph","created_at":"2026-07-05T02:30:59Z","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/2008.10870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Q-Learning is an important reinforcement learning algorithm, which involves training a deep neural network, called Deep Q-Network (DQN), to approximate the well-known Q-function. Although wildly successful under laboratory conditions, serious gaps between theory and practice as well as a lack of formal guarantees prevent its use in the real world. Adopting a dynamical systems perspective, we provide a theoretical analysis of a popular version of Deep Q-Learning under realistic and verifiable assumptions. More specifically, we prove an important result on the convergence of the algorithm, ","authors_text":"Arunselvan Ramaswamy, Eyke H\\\"ullermeier","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-25T07:59:20Z","title":"Deep Q-Learning: Theoretical Insights from an Asymptotic Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.10870","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":"sha256:441d6f0b19d4c69d7b2605ed1e14042f8c3c4bbdfc5ed32f56cef1a288c66880","target":"record","created_at":"2026-07-05T02:30:59Z","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":"ae4f5ba6600c233553d5ecf788cf50835e6f58f8517ea8b1528d461ce56672d5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-25T07:59:20Z","title_canon_sha256":"db82fbf5469a91f12a3ab9fb870821c8907808389739d58a1adeef89039065dd"},"schema_version":"1.0","source":{"id":"2008.10870","kind":"arxiv","version":2}},"canonical_sha256":"50530577b24a9bcc8aeef6ecefd29de7da31bb2191f911a0c0aa383a251eb8f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50530577b24a9bcc8aeef6ecefd29de7da31bb2191f911a0c0aa383a251eb8f7","first_computed_at":"2026-07-05T02:30:59.322437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:30:59.322437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S2oCk5/zInQjqnBWG1P5fPzZ9DSHaGe4yrG+oRRKhMZYpaJBQBJKMBEKQzhsrRBhr727208pU0fX9uX5Xa4ZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:30:59.322894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.10870","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:441d6f0b19d4c69d7b2605ed1e14042f8c3c4bbdfc5ed32f56cef1a288c66880","sha256:2effd9b55890314f911ac09c37f029a5cb6e775169d5b6d3cebfd63a560f5d1d"],"state_sha256":"6dd111268d3cb42e67de9fbb3c7615c9abfb0ae9859b5136f17a3110b7a3ae67"}