{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BCKMURT3VXVWSMXPNE4I24BNP4","short_pith_number":"pith:BCKMURT3","schema_version":"1.0","canonical_sha256":"0894ca467badeb6932ef69388d702d7f39ec686f833d50c4782fd3922d345ab7","source":{"kind":"arxiv","id":"2510.02590","version":2},"attestation_state":"computed","paper":{"title":"Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Hendawy, Carlo D'Eramo, Henrik Metternich, Jan Peters, Mahdi Kallel, Th\\'eo Vincent","submitted_at":"2025-10-02T21:48:01Z","abstract_excerpt":"The use of target networks is a popular approach for estimating value functions in deep Reinforcement Learning (RL). While effective, the target network remains a compromise solution that preserves stability at the cost of slowly moving targets, thus delaying learning. Conversely, using the online network as a bootstrapped target is intuitively appealing, albeit well-known to lead to unstable learning. In this work, we aim to obtain the best out of both worlds by introducing a novel update rule that computes the target using the MINimum estimate between the Target and Online network, giving ri"},"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":"2510.02590","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-02T21:48:01Z","cross_cats_sorted":[],"title_canon_sha256":"53ea747818d0c0861e242c0ac6a81cb760b5de4a7e0db5e0bcf7e9b115992347","abstract_canon_sha256":"7bfe54e19add2588847262bd95b4ceadeabe89f9f7630e00929dfa305c8d0b5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:34.255851Z","signature_b64":"rXTmUQ0jnrX0fD+Xo7eLZVVuAcGeHzOao2X0Z0ui4YWkv83QwjXx5cy1wNWpdUtINNmOvrc1aFtxnZS0NzwBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0894ca467badeb6932ef69388d702d7f39ec686f833d50c4782fd3922d345ab7","last_reissued_at":"2026-05-20T00:05:34.255210Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:34.255210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ahmed Hendawy, Carlo D'Eramo, Henrik Metternich, Jan Peters, Mahdi Kallel, Th\\'eo Vincent","submitted_at":"2025-10-02T21:48:01Z","abstract_excerpt":"The use of target networks is a popular approach for estimating value functions in deep Reinforcement Learning (RL). While effective, the target network remains a compromise solution that preserves stability at the cost of slowly moving targets, thus delaying learning. Conversely, using the online network as a bootstrapped target is intuitively appealing, albeit well-known to lead to unstable learning. In this work, we aim to obtain the best out of both worlds by introducing a novel update rule that computes the target using the MINimum estimate between the Target and Online network, giving ri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.02590","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/2510.02590/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":"2510.02590","created_at":"2026-05-20T00:05:34.255292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.02590v2","created_at":"2026-05-20T00:05:34.255292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.02590","created_at":"2026-05-20T00:05:34.255292+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCKMURT3VXVW","created_at":"2026-05-20T00:05:34.255292+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCKMURT3VXVWSMXP","created_at":"2026-05-20T00:05:34.255292+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCKMURT3","created_at":"2026-05-20T00:05:34.255292+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/BCKMURT3VXVWSMXPNE4I24BNP4","json":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4.json","graph_json":"https://pith.science/api/pith-number/BCKMURT3VXVWSMXPNE4I24BNP4/graph.json","events_json":"https://pith.science/api/pith-number/BCKMURT3VXVWSMXPNE4I24BNP4/events.json","paper":"https://pith.science/paper/BCKMURT3"},"agent_actions":{"view_html":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4","download_json":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4.json","view_paper":"https://pith.science/paper/BCKMURT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.02590&json=true","fetch_graph":"https://pith.science/api/pith-number/BCKMURT3VXVWSMXPNE4I24BNP4/graph.json","fetch_events":"https://pith.science/api/pith-number/BCKMURT3VXVWSMXPNE4I24BNP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4/action/storage_attestation","attest_author":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4/action/author_attestation","sign_citation":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4/action/citation_signature","submit_replication":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4/action/replication_record"}},"created_at":"2026-05-20T00:05:34.255292+00:00","updated_at":"2026-05-20T00:05:34.255292+00:00"}