{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RE62ZCVLJ6OJ5RPUDSAQGAWAE5","short_pith_number":"pith:RE62ZCVL","schema_version":"1.0","canonical_sha256":"893dac8aab4f9c9ec5f41c810302c02776ae88978494d3b176727f9418471cd2","source":{"kind":"arxiv","id":"2106.01134","version":1},"attestation_state":"computed","paper":{"title":"Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jizhou Lai, Wei Liao, Xiaohui Wei","submitted_at":"2021-06-02T13:05:24Z","abstract_excerpt":"An improvement of Q-learning is proposed in this paper. It is different from classic Q-learning in that the similarity between different states and actions is considered in the proposed method. During the training, a new updating mechanism is used, in which the Q value of the similar state-action pairs are updated synchronously. The proposed method can be used in combination with both tabular Q-learning function and deep Q-learning. And the results of numerical examples illustrate that compared to the classic Q-learning, the proposed method has a significantly better performance."},"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":"2106.01134","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-02T13:05:24Z","cross_cats_sorted":[],"title_canon_sha256":"5a81fa940c389795043d4772632bafc809466af4027885e3f33497a7fe12f678","abstract_canon_sha256":"ef5835dc810ce2e4f9933a5a2dde255ae09ef640801b64bdcbc0a1db3089e11d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:45:44.163372Z","signature_b64":"qOBc/TryqEAd0pbo0HTQMOG9zbus+qWA8AGeFmujGrefSGzyUI6IrB0ahfHB5iQ0Id+Fy2bTLimDh1F1RtKPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"893dac8aab4f9c9ec5f41c810302c02776ae88978494d3b176727f9418471cd2","last_reissued_at":"2026-07-05T02:45:44.162928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:45:44.162928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smooth Q-learning: Accelerate Convergence of Q-learning Using Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jizhou Lai, Wei Liao, Xiaohui Wei","submitted_at":"2021-06-02T13:05:24Z","abstract_excerpt":"An improvement of Q-learning is proposed in this paper. It is different from classic Q-learning in that the similarity between different states and actions is considered in the proposed method. During the training, a new updating mechanism is used, in which the Q value of the similar state-action pairs are updated synchronously. The proposed method can be used in combination with both tabular Q-learning function and deep Q-learning. And the results of numerical examples illustrate that compared to the classic Q-learning, the proposed method has a significantly better performance."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01134","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.01134/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":"2106.01134","created_at":"2026-07-05T02:45:44.162986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01134v1","created_at":"2026-07-05T02:45:44.162986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01134","created_at":"2026-07-05T02:45:44.162986+00:00"},{"alias_kind":"pith_short_12","alias_value":"RE62ZCVLJ6OJ","created_at":"2026-07-05T02:45:44.162986+00:00"},{"alias_kind":"pith_short_16","alias_value":"RE62ZCVLJ6OJ5RPU","created_at":"2026-07-05T02:45:44.162986+00:00"},{"alias_kind":"pith_short_8","alias_value":"RE62ZCVL","created_at":"2026-07-05T02:45:44.162986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18518","citing_title":"PSyGenTAB: A Privacy-Preserving Framework for Synthetic Clinical Tabular Data Generation via Constrained Optimization","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RE62ZCVLJ6OJ5RPUDSAQGAWAE5","json":"https://pith.science/pith/RE62ZCVLJ6OJ5RPUDSAQGAWAE5.json","graph_json":"https://pith.science/api/pith-number/RE62ZCVLJ6OJ5RPUDSAQGAWAE5/graph.json","events_json":"https://pith.science/api/pith-number/RE62ZCVLJ6OJ5RPUDSAQGAWAE5/events.json","paper":"https://pith.science/paper/RE62ZCVL"},"agent_actions":{"view_html":"https://pith.science/pith/RE62ZCVLJ6OJ5RPUDSAQGAWAE5","download_json":"https://pith.science/pith/RE62ZCVLJ6OJ5RPUDSAQGAWAE5.json","view_paper":"https://pith.science/paper/RE62ZCVL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01134&json=true","fetch_graph":"https://pith.science/api/pith-number/RE62ZCVLJ6OJ5RPUDSAQGAWAE5/graph.json","fetch_events":"https://pith.science/api/pith-number/RE62ZCVLJ6OJ5RPUDSAQGAWAE5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RE62ZCVLJ6OJ5RPUDSAQGAWAE5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RE62ZCVLJ6OJ5RPUDSAQGAWAE5/action/storage_attestation","attest_author":"https://pith.science/pith/RE62ZCVLJ6OJ5RPUDSAQGAWAE5/action/author_attestation","sign_citation":"https://pith.science/pith/RE62ZCVLJ6OJ5RPUDSAQGAWAE5/action/citation_signature","submit_replication":"https://pith.science/pith/RE62ZCVLJ6OJ5RPUDSAQGAWAE5/action/replication_record"}},"created_at":"2026-07-05T02:45:44.162986+00:00","updated_at":"2026-07-05T02:45:44.162986+00:00"}