{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BCKMURT3VXVWSMXPNE4I24BNP4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7bfe54e19add2588847262bd95b4ceadeabe89f9f7630e00929dfa305c8d0b5e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-02T21:48:01Z","title_canon_sha256":"53ea747818d0c0861e242c0ac6a81cb760b5de4a7e0db5e0bcf7e9b115992347"},"schema_version":"1.0","source":{"id":"2510.02590","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.02590","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"2510.02590v2","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.02590","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"BCKMURT3VXVW","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"pith_short_16","alias_value":"BCKMURT3VXVWSMXP","created_at":"2026-05-20T00:05:34Z"},{"alias_kind":"pith_short_8","alias_value":"BCKMURT3","created_at":"2026-05-20T00:05:34Z"}],"graph_snapshots":[{"event_id":"sha256:7eae8793cc34903702cd84be86062566ce9f577ade174655714622d8b859e232","target":"graph","created_at":"2026-05-20T00:05:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.02590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ahmed Hendawy, Carlo D'Eramo, Henrik Metternich, Jan Peters, Mahdi Kallel, Th\\'eo Vincent","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-02T21:48:01Z","title":"Use the Online Network If You Can: Towards Fast and Stable Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.02590","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3487de9eebff3dd61f7f391049b3aff123474e4d1e46fc675cbd43aba35df640","target":"record","created_at":"2026-05-20T00:05:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7bfe54e19add2588847262bd95b4ceadeabe89f9f7630e00929dfa305c8d0b5e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-02T21:48:01Z","title_canon_sha256":"53ea747818d0c0861e242c0ac6a81cb760b5de4a7e0db5e0bcf7e9b115992347"},"schema_version":"1.0","source":{"id":"2510.02590","kind":"arxiv","version":2}},"canonical_sha256":"0894ca467badeb6932ef69388d702d7f39ec686f833d50c4782fd3922d345ab7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0894ca467badeb6932ef69388d702d7f39ec686f833d50c4782fd3922d345ab7","first_computed_at":"2026-05-20T00:05:34.255210Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:34.255210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rXTmUQ0jnrX0fD+Xo7eLZVVuAcGeHzOao2X0Z0ui4YWkv83QwjXx5cy1wNWpdUtINNmOvrc1aFtxnZS0NzwBCA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:34.255851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.02590","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3487de9eebff3dd61f7f391049b3aff123474e4d1e46fc675cbd43aba35df640","sha256:7eae8793cc34903702cd84be86062566ce9f577ade174655714622d8b859e232"],"state_sha256":"c32410a3c5c4227f95543fce46a9b057623def59d11498a9657a29ef156d23d1"}