{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KBJQK55SJKN4ZCXO63WO7UU547","short_pith_number":"pith:KBJQK55S","schema_version":"1.0","canonical_sha256":"50530577b24a9bcc8aeef6ecefd29de7da31bb2191f911a0c0aa383a251eb8f7","source":{"kind":"arxiv","id":"2008.10870","version":2},"attestation_state":"computed","paper":{"title":"Deep Q-Learning: Theoretical Insights from an Asymptotic Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arunselvan Ramaswamy, Eyke H\\\"ullermeier","submitted_at":"2020-08-25T07:59:20Z","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, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2008.10870","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-25T07:59:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"db82fbf5469a91f12a3ab9fb870821c8907808389739d58a1adeef89039065dd","abstract_canon_sha256":"ae4f5ba6600c233553d5ecf788cf50835e6f58f8517ea8b1528d461ce56672d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:59.322894Z","signature_b64":"S2oCk5/zInQjqnBWG1P5fPzZ9DSHaGe4yrG+oRRKhMZYpaJBQBJKMBEKQzhsrRBhr727208pU0fX9uX5Xa4ZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50530577b24a9bcc8aeef6ecefd29de7da31bb2191f911a0c0aa383a251eb8f7","last_reissued_at":"2026-07-05T02:30:59.322437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:59.322437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Q-Learning: Theoretical Insights from an Asymptotic Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Arunselvan Ramaswamy, Eyke H\\\"ullermeier","submitted_at":"2020-08-25T07:59:20Z","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, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.10870","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.10870/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2008.10870","created_at":"2026-07-05T02:30:59.322502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.10870v2","created_at":"2026-07-05T02:30:59.322502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.10870","created_at":"2026-07-05T02:30:59.322502+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBJQK55SJKN4","created_at":"2026-07-05T02:30:59.322502+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBJQK55SJKN4ZCXO","created_at":"2026-07-05T02:30:59.322502+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBJQK55S","created_at":"2026-07-05T02:30:59.322502+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.10861","citing_title":"Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBJQK55SJKN4ZCXO63WO7UU547","json":"https://pith.science/pith/KBJQK55SJKN4ZCXO63WO7UU547.json","graph_json":"https://pith.science/api/pith-number/KBJQK55SJKN4ZCXO63WO7UU547/graph.json","events_json":"https://pith.science/api/pith-number/KBJQK55SJKN4ZCXO63WO7UU547/events.json","paper":"https://pith.science/paper/KBJQK55S"},"agent_actions":{"view_html":"https://pith.science/pith/KBJQK55SJKN4ZCXO63WO7UU547","download_json":"https://pith.science/pith/KBJQK55SJKN4ZCXO63WO7UU547.json","view_paper":"https://pith.science/paper/KBJQK55S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.10870&json=true","fetch_graph":"https://pith.science/api/pith-number/KBJQK55SJKN4ZCXO63WO7UU547/graph.json","fetch_events":"https://pith.science/api/pith-number/KBJQK55SJKN4ZCXO63WO7UU547/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBJQK55SJKN4ZCXO63WO7UU547/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBJQK55SJKN4ZCXO63WO7UU547/action/storage_attestation","attest_author":"https://pith.science/pith/KBJQK55SJKN4ZCXO63WO7UU547/action/author_attestation","sign_citation":"https://pith.science/pith/KBJQK55SJKN4ZCXO63WO7UU547/action/citation_signature","submit_replication":"https://pith.science/pith/KBJQK55SJKN4ZCXO63WO7UU547/action/replication_record"}},"created_at":"2026-07-05T02:30:59.322502+00:00","updated_at":"2026-07-05T02:30:59.322502+00:00"}