{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RTCSDY7CLYMBBZEO6CXBF77EKC","short_pith_number":"pith:RTCSDY7C","schema_version":"1.0","canonical_sha256":"8cc521e3e25e1810e48ef0ae12ffe4509622d07f7d48b9e87af26feea379ea29","source":{"kind":"arxiv","id":"2210.12282","version":2},"attestation_state":"computed","paper":{"title":"Bridging the Gap Between Target Networks and Functional Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Piche, Christopher Pal, Gian Maria Marconi, Joseph Marino, Mohammad Emtiyaz Khan, Rafael Pardinas, Valentin Thomas","submitted_at":"2022-10-21T22:27:07Z","abstract_excerpt":"Bootstrapping is behind much of the successes of Deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to stabilize training by using an additional set of lagging parameters to estimate the target values. Despite the popularity of Target Networks, their effect on the optimization is still misunderstood. In this work, we show that they act as an implicit regularizer. This regularizer has disadvantages such as being inflexible and non convex. To overcome these issues, w"},"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":"2210.12282","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-21T22:27:07Z","cross_cats_sorted":[],"title_canon_sha256":"a2cf7c247c77ed7a74417de6a37814d150458ef2dbd7dcb44e5cc7959c92dacd","abstract_canon_sha256":"bd9030b041bdc76a924e7c8ee0771a4224f72d4baabf9e756e5fd318eed39be0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:51.552206Z","signature_b64":"hSUvllW5YDSAOt6hRUv9Nay0bTGy7CR3ILbcZncz0gAmmtowXY+U5PkcAnyW8RxojrHftPpL2OrANNbsav3WCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cc521e3e25e1810e48ef0ae12ffe4509622d07f7d48b9e87af26feea379ea29","last_reissued_at":"2026-07-05T07:29:51.551724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:51.551724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging the Gap Between Target Networks and Functional Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Piche, Christopher Pal, Gian Maria Marconi, Joseph Marino, Mohammad Emtiyaz Khan, Rafael Pardinas, Valentin Thomas","submitted_at":"2022-10-21T22:27:07Z","abstract_excerpt":"Bootstrapping is behind much of the successes of Deep Reinforcement Learning. However, learning the value function via bootstrapping often leads to unstable training due to fast-changing target values. Target Networks are employed to stabilize training by using an additional set of lagging parameters to estimate the target values. Despite the popularity of Target Networks, their effect on the optimization is still misunderstood. In this work, we show that they act as an implicit regularizer. This regularizer has disadvantages such as being inflexible and non convex. To overcome these issues, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12282","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/2210.12282/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":"2210.12282","created_at":"2026-07-05T07:29:51.551791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12282v2","created_at":"2026-07-05T07:29:51.551791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12282","created_at":"2026-07-05T07:29:51.551791+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTCSDY7CLYMB","created_at":"2026-07-05T07:29:51.551791+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTCSDY7CLYMBBZEO","created_at":"2026-07-05T07:29:51.551791+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTCSDY7C","created_at":"2026-07-05T07:29:51.551791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTCSDY7CLYMBBZEO6CXBF77EKC","json":"https://pith.science/pith/RTCSDY7CLYMBBZEO6CXBF77EKC.json","graph_json":"https://pith.science/api/pith-number/RTCSDY7CLYMBBZEO6CXBF77EKC/graph.json","events_json":"https://pith.science/api/pith-number/RTCSDY7CLYMBBZEO6CXBF77EKC/events.json","paper":"https://pith.science/paper/RTCSDY7C"},"agent_actions":{"view_html":"https://pith.science/pith/RTCSDY7CLYMBBZEO6CXBF77EKC","download_json":"https://pith.science/pith/RTCSDY7CLYMBBZEO6CXBF77EKC.json","view_paper":"https://pith.science/paper/RTCSDY7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12282&json=true","fetch_graph":"https://pith.science/api/pith-number/RTCSDY7CLYMBBZEO6CXBF77EKC/graph.json","fetch_events":"https://pith.science/api/pith-number/RTCSDY7CLYMBBZEO6CXBF77EKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTCSDY7CLYMBBZEO6CXBF77EKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTCSDY7CLYMBBZEO6CXBF77EKC/action/storage_attestation","attest_author":"https://pith.science/pith/RTCSDY7CLYMBBZEO6CXBF77EKC/action/author_attestation","sign_citation":"https://pith.science/pith/RTCSDY7CLYMBBZEO6CXBF77EKC/action/citation_signature","submit_replication":"https://pith.science/pith/RTCSDY7CLYMBBZEO6CXBF77EKC/action/replication_record"}},"created_at":"2026-07-05T07:29:51.551791+00:00","updated_at":"2026-07-05T07:29:51.551791+00:00"}