{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C34EDGIUEC7YULC6RQ4PPLSP3L","short_pith_number":"pith:C34EDGIU","schema_version":"1.0","canonical_sha256":"16f841991420bf8a2c5e8c38f7ae4fdafae5fade05977c3d8edb9295d8c1379d","source":{"kind":"arxiv","id":"2402.09078","version":2},"attestation_state":"computed","paper":{"title":"Exploiting Estimation Bias in Clipped Double Q-Learning for Continous Control Reinforcement Learning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alberto Dalla Libera, Alberto Sinigaglia, Gian Antonio Susto, Niccol\\`o Turcato, Ruggero Carli","submitted_at":"2024-02-14T10:44:03Z","abstract_excerpt":"Continuous control Deep Reinforcement Learning (RL) approaches are known to suffer from estimation biases, leading to suboptimal policies. This paper introduces innovative methods in RL, focusing on addressing and exploiting estimation biases in Actor-Critic methods for continuous control tasks, using Deep Double Q-Learning. We design a Bias Exploiting (BE) mechanism to dynamically select the most advantageous estimation bias during training of the RL agent. Most State-of-the-art Deep RL algorithms can be equipped with the BE mechanism, without hindering performance or computational complexity"},"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":"2402.09078","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-14T10:44:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bd6d1a0e74e5fb3155d7a9b5cb1edb22a002043552ed0c23f86da28bd89ea414","abstract_canon_sha256":"57216ec722fe77c861c67627b348ee8fb60f87bea4cb75abd332f586aba84e08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:07.465795Z","signature_b64":"jYHx2/8+kYPH/FThdYHCEiP6Aqvmim8liIuHV13tw0zwS8fdL9LM86x2v465+d4Gwmv7qi4YnKSpKL2XdAqBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16f841991420bf8a2c5e8c38f7ae4fdafae5fade05977c3d8edb9295d8c1379d","last_reissued_at":"2026-07-05T09:19:07.465310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:07.465310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Estimation Bias in Clipped Double Q-Learning for Continous Control Reinforcement Learning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alberto Dalla Libera, Alberto Sinigaglia, Gian Antonio Susto, Niccol\\`o Turcato, Ruggero Carli","submitted_at":"2024-02-14T10:44:03Z","abstract_excerpt":"Continuous control Deep Reinforcement Learning (RL) approaches are known to suffer from estimation biases, leading to suboptimal policies. This paper introduces innovative methods in RL, focusing on addressing and exploiting estimation biases in Actor-Critic methods for continuous control tasks, using Deep Double Q-Learning. We design a Bias Exploiting (BE) mechanism to dynamically select the most advantageous estimation bias during training of the RL agent. Most State-of-the-art Deep RL algorithms can be equipped with the BE mechanism, without hindering performance or computational complexity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09078","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/2402.09078/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":"2402.09078","created_at":"2026-07-05T09:19:07.465378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09078v2","created_at":"2026-07-05T09:19:07.465378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09078","created_at":"2026-07-05T09:19:07.465378+00:00"},{"alias_kind":"pith_short_12","alias_value":"C34EDGIUEC7Y","created_at":"2026-07-05T09:19:07.465378+00:00"},{"alias_kind":"pith_short_16","alias_value":"C34EDGIUEC7YULC6","created_at":"2026-07-05T09:19:07.465378+00:00"},{"alias_kind":"pith_short_8","alias_value":"C34EDGIU","created_at":"2026-07-05T09:19:07.465378+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/C34EDGIUEC7YULC6RQ4PPLSP3L","json":"https://pith.science/pith/C34EDGIUEC7YULC6RQ4PPLSP3L.json","graph_json":"https://pith.science/api/pith-number/C34EDGIUEC7YULC6RQ4PPLSP3L/graph.json","events_json":"https://pith.science/api/pith-number/C34EDGIUEC7YULC6RQ4PPLSP3L/events.json","paper":"https://pith.science/paper/C34EDGIU"},"agent_actions":{"view_html":"https://pith.science/pith/C34EDGIUEC7YULC6RQ4PPLSP3L","download_json":"https://pith.science/pith/C34EDGIUEC7YULC6RQ4PPLSP3L.json","view_paper":"https://pith.science/paper/C34EDGIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09078&json=true","fetch_graph":"https://pith.science/api/pith-number/C34EDGIUEC7YULC6RQ4PPLSP3L/graph.json","fetch_events":"https://pith.science/api/pith-number/C34EDGIUEC7YULC6RQ4PPLSP3L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C34EDGIUEC7YULC6RQ4PPLSP3L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C34EDGIUEC7YULC6RQ4PPLSP3L/action/storage_attestation","attest_author":"https://pith.science/pith/C34EDGIUEC7YULC6RQ4PPLSP3L/action/author_attestation","sign_citation":"https://pith.science/pith/C34EDGIUEC7YULC6RQ4PPLSP3L/action/citation_signature","submit_replication":"https://pith.science/pith/C34EDGIUEC7YULC6RQ4PPLSP3L/action/replication_record"}},"created_at":"2026-07-05T09:19:07.465378+00:00","updated_at":"2026-07-05T09:19:07.465378+00:00"}