{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MMLLJUKLW65I64EIHUPS7D7DPP","short_pith_number":"pith:MMLLJUKL","schema_version":"1.0","canonical_sha256":"6316b4d14bb7ba8f70883d1f2f8fe37bc62ab020264443de9aaedf751717f2ef","source":{"kind":"arxiv","id":"2109.02517","version":2},"attestation_state":"computed","paper":{"title":"Error Controlled Actor-Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changjing Shang, Changle Zhou, Chih-Min Lin, Fei Chao, Longzhi Yang, Xiang Chang, Xingen Gao, Zhen Ge","submitted_at":"2021-09-06T14:51:20Z","abstract_excerpt":"On error of value function inevitably causes an overestimation phenomenon and has a negative impact on the convergence of the algorithms. To mitigate the negative effects of the approximation error, we propose Error Controlled Actor-critic which ensures confining the approximation error in value function. We present an analysis of how the approximation error can hinder the optimization process of actor-critic methods.Then, we derive an upper boundary of the approximation error of Q function approximator and find that the error can be lowered by restricting on the KL-divergence between every tw"},"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":"2109.02517","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-06T14:51:20Z","cross_cats_sorted":[],"title_canon_sha256":"bdc2f9d9c3562407958e6b60667f23449f816b69a758adc622d6ceba77afcef2","abstract_canon_sha256":"10bc74d91e978c7d70e481f4e118842fe3aaa9ad22fdfa862fad4c7f4cc2f023"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:17.515294Z","signature_b64":"Rx6heDbXBgGNoJxrQcae2tA5Xdh8Vt8n4z/mBb38dLMJAY8ywCvGrbv20ieFdbiDuMdW7zFJUl29u2QIwvp0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6316b4d14bb7ba8f70883d1f2f8fe37bc62ab020264443de9aaedf751717f2ef","last_reissued_at":"2026-07-05T03:12:17.514765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:17.514765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Error Controlled Actor-Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Changjing Shang, Changle Zhou, Chih-Min Lin, Fei Chao, Longzhi Yang, Xiang Chang, Xingen Gao, Zhen Ge","submitted_at":"2021-09-06T14:51:20Z","abstract_excerpt":"On error of value function inevitably causes an overestimation phenomenon and has a negative impact on the convergence of the algorithms. To mitigate the negative effects of the approximation error, we propose Error Controlled Actor-critic which ensures confining the approximation error in value function. We present an analysis of how the approximation error can hinder the optimization process of actor-critic methods.Then, we derive an upper boundary of the approximation error of Q function approximator and find that the error can be lowered by restricting on the KL-divergence between every tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02517","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/2109.02517/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":"2109.02517","created_at":"2026-07-05T03:12:17.514825+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.02517v2","created_at":"2026-07-05T03:12:17.514825+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02517","created_at":"2026-07-05T03:12:17.514825+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMLLJUKLW65I","created_at":"2026-07-05T03:12:17.514825+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMLLJUKLW65I64EI","created_at":"2026-07-05T03:12:17.514825+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMLLJUKL","created_at":"2026-07-05T03:12:17.514825+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/MMLLJUKLW65I64EIHUPS7D7DPP","json":"https://pith.science/pith/MMLLJUKLW65I64EIHUPS7D7DPP.json","graph_json":"https://pith.science/api/pith-number/MMLLJUKLW65I64EIHUPS7D7DPP/graph.json","events_json":"https://pith.science/api/pith-number/MMLLJUKLW65I64EIHUPS7D7DPP/events.json","paper":"https://pith.science/paper/MMLLJUKL"},"agent_actions":{"view_html":"https://pith.science/pith/MMLLJUKLW65I64EIHUPS7D7DPP","download_json":"https://pith.science/pith/MMLLJUKLW65I64EIHUPS7D7DPP.json","view_paper":"https://pith.science/paper/MMLLJUKL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.02517&json=true","fetch_graph":"https://pith.science/api/pith-number/MMLLJUKLW65I64EIHUPS7D7DPP/graph.json","fetch_events":"https://pith.science/api/pith-number/MMLLJUKLW65I64EIHUPS7D7DPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMLLJUKLW65I64EIHUPS7D7DPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMLLJUKLW65I64EIHUPS7D7DPP/action/storage_attestation","attest_author":"https://pith.science/pith/MMLLJUKLW65I64EIHUPS7D7DPP/action/author_attestation","sign_citation":"https://pith.science/pith/MMLLJUKLW65I64EIHUPS7D7DPP/action/citation_signature","submit_replication":"https://pith.science/pith/MMLLJUKLW65I64EIHUPS7D7DPP/action/replication_record"}},"created_at":"2026-07-05T03:12:17.514825+00:00","updated_at":"2026-07-05T03:12:17.514825+00:00"}