{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3ZAALRNOL742DVOCR7TLDW62VE","short_pith_number":"pith:3ZAALRNO","schema_version":"1.0","canonical_sha256":"de4005c5ae5ff9a1d5c28fe6b1dbdaa903031a7f90558c317d889d763f80df07","source":{"kind":"arxiv","id":"2209.11303","version":1},"attestation_state":"computed","paper":{"title":"An Investigation of the Bias-Variance Tradeoff in Meta-Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gregory Farquhar, Jacob Beck, Jakob Foerster, Risto Vuorio, Shimon Whiteson","submitted_at":"2022-09-22T20:33:05Z","abstract_excerpt":"Meta-gradients provide a general approach for optimizing the meta-parameters of reinforcement learning (RL) algorithms. Estimation of meta-gradients is central to the performance of these meta-algorithms, and has been studied in the setting of MAML-style short-horizon meta-RL problems. In this context, prior work has investigated the estimation of the Hessian of the RL objective, as well as tackling the problem of credit assignment to pre-adaptation behavior by making a sampling correction. However, we show that Hessian estimation, implemented for example by DiCE and its variants, always adds "},"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":"2209.11303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-22T20:33:05Z","cross_cats_sorted":[],"title_canon_sha256":"5207b647ed4447a31e79bf08689c313533ecce0086070796ec5e9196f70f19fb","abstract_canon_sha256":"30a471526ad38a1ef6a74ac5af0f1d3a0d329cb8efb942c9f032fa62c60ed11b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:19.091398Z","signature_b64":"n2v5nC9ueE+1clcb89tj3FwA7rdTTND8JPnfy5JUM5fg5vQi8gSJz3B9JaoedTzZkaD9S7EfcxhK9PnRas4BDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de4005c5ae5ff9a1d5c28fe6b1dbdaa903031a7f90558c317d889d763f80df07","last_reissued_at":"2026-07-05T05:00:19.090925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:19.090925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Investigation of the Bias-Variance Tradeoff in Meta-Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gregory Farquhar, Jacob Beck, Jakob Foerster, Risto Vuorio, Shimon Whiteson","submitted_at":"2022-09-22T20:33:05Z","abstract_excerpt":"Meta-gradients provide a general approach for optimizing the meta-parameters of reinforcement learning (RL) algorithms. Estimation of meta-gradients is central to the performance of these meta-algorithms, and has been studied in the setting of MAML-style short-horizon meta-RL problems. In this context, prior work has investigated the estimation of the Hessian of the RL objective, as well as tackling the problem of credit assignment to pre-adaptation behavior by making a sampling correction. However, we show that Hessian estimation, implemented for example by DiCE and its variants, always adds "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11303","kind":"arxiv","version":1},"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/2209.11303/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":"2209.11303","created_at":"2026-07-05T05:00:19.090991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.11303v1","created_at":"2026-07-05T05:00:19.090991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11303","created_at":"2026-07-05T05:00:19.090991+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZAALRNOL742","created_at":"2026-07-05T05:00:19.090991+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZAALRNOL742DVOC","created_at":"2026-07-05T05:00:19.090991+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZAALRNO","created_at":"2026-07-05T05:00:19.090991+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/3ZAALRNOL742DVOCR7TLDW62VE","json":"https://pith.science/pith/3ZAALRNOL742DVOCR7TLDW62VE.json","graph_json":"https://pith.science/api/pith-number/3ZAALRNOL742DVOCR7TLDW62VE/graph.json","events_json":"https://pith.science/api/pith-number/3ZAALRNOL742DVOCR7TLDW62VE/events.json","paper":"https://pith.science/paper/3ZAALRNO"},"agent_actions":{"view_html":"https://pith.science/pith/3ZAALRNOL742DVOCR7TLDW62VE","download_json":"https://pith.science/pith/3ZAALRNOL742DVOCR7TLDW62VE.json","view_paper":"https://pith.science/paper/3ZAALRNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.11303&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZAALRNOL742DVOCR7TLDW62VE/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZAALRNOL742DVOCR7TLDW62VE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZAALRNOL742DVOCR7TLDW62VE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZAALRNOL742DVOCR7TLDW62VE/action/storage_attestation","attest_author":"https://pith.science/pith/3ZAALRNOL742DVOCR7TLDW62VE/action/author_attestation","sign_citation":"https://pith.science/pith/3ZAALRNOL742DVOCR7TLDW62VE/action/citation_signature","submit_replication":"https://pith.science/pith/3ZAALRNOL742DVOCR7TLDW62VE/action/replication_record"}},"created_at":"2026-07-05T05:00:19.090991+00:00","updated_at":"2026-07-05T05:00:19.090991+00:00"}