{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:3OFGGGW6TOBJKBDHUP7MA4N2JY","short_pith_number":"pith:3OFGGGW6","schema_version":"1.0","canonical_sha256":"db8a631ade9b82950467a3fec071ba4e388184c0405e9b8220cd32c67d26dfc7","source":{"kind":"arxiv","id":"1711.07478","version":1},"attestation_state":"computed","paper":{"title":"Implementing the Deep Q-Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"James MacGlashan, Melrose Roderick, Stefanie Tellex","submitted_at":"2017-11-20T16:40:33Z","abstract_excerpt":"The Deep Q-Network proposed by Mnih et al. [2015] has become a benchmark and building point for much deep reinforcement learning research. However, replicating results for complex systems is often challenging since original scientific publications are not always able to describe in detail every important parameter setting and software engineering solution. In this paper, we present results from our work reproducing the results of the DQN paper. We highlight key areas in the implementation that were not covered in great detail in the original paper to make it easier for researchers to replicate"},"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":"1711.07478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-20T16:40:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bf9fea90c258a70f1756fa137cc6292259ee3bf829a506e31f0401495100a444","abstract_canon_sha256":"f95c6b4ccad65a030b33e45e154064192142a94ff3b4a6082b9b473fa12bfc00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:58.870712Z","signature_b64":"y2/ZegQubt7eM5mmESNB5DvvbGyXsx04uvpZGo7c3EGqolq8nVkPDlCNsQLKR3668RJFQdFMhBN52Ez9neKxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db8a631ade9b82950467a3fec071ba4e388184c0405e9b8220cd32c67d26dfc7","last_reissued_at":"2026-05-18T00:29:58.870099Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:58.870099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implementing the Deep Q-Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"James MacGlashan, Melrose Roderick, Stefanie Tellex","submitted_at":"2017-11-20T16:40:33Z","abstract_excerpt":"The Deep Q-Network proposed by Mnih et al. [2015] has become a benchmark and building point for much deep reinforcement learning research. However, replicating results for complex systems is often challenging since original scientific publications are not always able to describe in detail every important parameter setting and software engineering solution. In this paper, we present results from our work reproducing the results of the DQN paper. We highlight key areas in the implementation that were not covered in great detail in the original paper to make it easier for researchers to replicate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.07478","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1711.07478","created_at":"2026-05-18T00:29:58.870194+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.07478v1","created_at":"2026-05-18T00:29:58.870194+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.07478","created_at":"2026-05-18T00:29:58.870194+00:00"},{"alias_kind":"pith_short_12","alias_value":"3OFGGGW6TOBJ","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_16","alias_value":"3OFGGGW6TOBJKBDH","created_at":"2026-05-18T12:30:58.224056+00:00"},{"alias_kind":"pith_short_8","alias_value":"3OFGGGW6","created_at":"2026-05-18T12:30:58.224056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02698","citing_title":"Multi-Agent Reinforcement Learning for Dynamic Pricing in Supply Chains: Benchmarking Strategic Agent Behaviours under Realistically Simulated Market Conditions","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3OFGGGW6TOBJKBDHUP7MA4N2JY","json":"https://pith.science/pith/3OFGGGW6TOBJKBDHUP7MA4N2JY.json","graph_json":"https://pith.science/api/pith-number/3OFGGGW6TOBJKBDHUP7MA4N2JY/graph.json","events_json":"https://pith.science/api/pith-number/3OFGGGW6TOBJKBDHUP7MA4N2JY/events.json","paper":"https://pith.science/paper/3OFGGGW6"},"agent_actions":{"view_html":"https://pith.science/pith/3OFGGGW6TOBJKBDHUP7MA4N2JY","download_json":"https://pith.science/pith/3OFGGGW6TOBJKBDHUP7MA4N2JY.json","view_paper":"https://pith.science/paper/3OFGGGW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.07478&json=true","fetch_graph":"https://pith.science/api/pith-number/3OFGGGW6TOBJKBDHUP7MA4N2JY/graph.json","fetch_events":"https://pith.science/api/pith-number/3OFGGGW6TOBJKBDHUP7MA4N2JY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3OFGGGW6TOBJKBDHUP7MA4N2JY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3OFGGGW6TOBJKBDHUP7MA4N2JY/action/storage_attestation","attest_author":"https://pith.science/pith/3OFGGGW6TOBJKBDHUP7MA4N2JY/action/author_attestation","sign_citation":"https://pith.science/pith/3OFGGGW6TOBJKBDHUP7MA4N2JY/action/citation_signature","submit_replication":"https://pith.science/pith/3OFGGGW6TOBJKBDHUP7MA4N2JY/action/replication_record"}},"created_at":"2026-05-18T00:29:58.870194+00:00","updated_at":"2026-05-18T00:29:58.870194+00:00"}