{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BCKMURT3VXVWSMXPNE4I24BNP4","short_pith_number":"pith:BCKMURT3","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"},"canonical_sha256":"0894ca467badeb6932ef69388d702d7f39ec686f833d50c4782fd3922d345ab7","source":{"kind":"arxiv","id":"2510.02590","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BCKMURT3VXVWSMXPNE4I24BNP4","target":"record","payload":{"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"},"canonical_sha256":"0894ca467badeb6932ef69388d702d7f39ec686f833d50c4782fd3922d345ab7","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"},"source_kind":"arxiv","source_id":"2510.02590","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZrhY4mIj68Z6XC4Qbu5FAZOVeMMdSQ3ONt4XKpbG7Cp6kWAnOwg9UONjImHms2hCFmBQi0Z9LFQhUhdKO0B3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:42:04.431441Z"},"content_sha256":"3487de9eebff3dd61f7f391049b3aff123474e4d1e46fc675cbd43aba35df640","schema_version":"1.0","event_id":"sha256:3487de9eebff3dd61f7f391049b3aff123474e4d1e46fc675cbd43aba35df640"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BCKMURT3VXVWSMXPNE4I24BNP4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rDNHLId6NTMApIxLPoQwDGFJtlidmzxAzHVyUZLJDUyIxhbnMQAjiGSB1oIcbFC8NlDf5BbV/i5PxvzHZ6sqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T23:42:04.432194Z"},"content_sha256":"7eae8793cc34903702cd84be86062566ce9f577ade174655714622d8b859e232","schema_version":"1.0","event_id":"sha256:7eae8793cc34903702cd84be86062566ce9f577ade174655714622d8b859e232"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4/bundle.json","state_url":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCKMURT3VXVWSMXPNE4I24BNP4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T23:42:04Z","links":{"resolver":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4","bundle":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4/bundle.json","state":"https://pith.science/pith/BCKMURT3VXVWSMXPNE4I24BNP4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCKMURT3VXVWSMXPNE4I24BNP4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bfX7N5g/Dg0jd/de1KUXpC+06TJ9Fv3vBM84MmKabrkOBroXy/ntaS0V/iTRDI4SOpnumpn2D+2KnYY7vT5mCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T23:42:04.435921Z","bundle_sha256":"ed14a8e85502f84bbf282722d10e208383493442181704680ff7de08c66fba3e"}}