{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VK3VN63RNXZODHUHO6EFFUJ3LZ","short_pith_number":"pith:VK3VN63R","schema_version":"1.0","canonical_sha256":"aab756fb716df2e19e87778852d13b5e73f32101f2c4c2cbcfeb66093618900b","source":{"kind":"arxiv","id":"1805.09801","version":1},"attestation_state":"computed","paper":{"title":"Meta-Gradient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Silver, Hado van Hasselt, Zhongwen Xu","submitted_at":"2018-05-24T17:45:11Z","abstract_excerpt":"The goal of reinforcement learning algorithms is to estimate and/or optimise the value function. However, unlike supervised learning, no teacher or oracle is available to provide the true value function. Instead, the majority of reinforcement learning algorithms estimate and/or optimise a proxy for the value function. This proxy is typically based on a sampled and bootstrapped approximation to the true value function, known as a return. The particular choice of return is one of the chief components determining the nature of the algorithm: the rate at which future rewards are discounted; when a"},"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":"1805.09801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-24T17:45:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"749ac15387e81fba1f2e10652dba71c41b5c7fc42fe35dea81db4d410109a0bf","abstract_canon_sha256":"06a9e66d5608d62b737325f42f10257e8bc3299ceb42afdeba0d12f78e905f6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:02.791501Z","signature_b64":"2t8BfGIy0AzkuzWXYuT9xdjGW4WJe/U8ai/6a9s2ModSfgo6On1WeTjF7Ktc97q2B521B+H/M/B3/0LO6tBdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aab756fb716df2e19e87778852d13b5e73f32101f2c4c2cbcfeb66093618900b","last_reissued_at":"2026-05-18T00:15:02.790749Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:02.790749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Gradient Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Silver, Hado van Hasselt, Zhongwen Xu","submitted_at":"2018-05-24T17:45:11Z","abstract_excerpt":"The goal of reinforcement learning algorithms is to estimate and/or optimise the value function. However, unlike supervised learning, no teacher or oracle is available to provide the true value function. Instead, the majority of reinforcement learning algorithms estimate and/or optimise a proxy for the value function. This proxy is typically based on a sampled and bootstrapped approximation to the true value function, known as a return. The particular choice of return is one of the chief components determining the nature of the algorithm: the rate at which future rewards are discounted; when a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09801","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":""},"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":"1805.09801","created_at":"2026-05-18T00:15:02.790849+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09801v1","created_at":"2026-05-18T00:15:02.790849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09801","created_at":"2026-05-18T00:15:02.790849+00:00"},{"alias_kind":"pith_short_12","alias_value":"VK3VN63RNXZO","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VK3VN63RNXZODHUH","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VK3VN63R","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.02908","citing_title":"On Inductive Biases in Deep Reinforcement Learning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ","json":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ.json","graph_json":"https://pith.science/api/pith-number/VK3VN63RNXZODHUHO6EFFUJ3LZ/graph.json","events_json":"https://pith.science/api/pith-number/VK3VN63RNXZODHUHO6EFFUJ3LZ/events.json","paper":"https://pith.science/paper/VK3VN63R"},"agent_actions":{"view_html":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ","download_json":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ.json","view_paper":"https://pith.science/paper/VK3VN63R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09801&json=true","fetch_graph":"https://pith.science/api/pith-number/VK3VN63RNXZODHUHO6EFFUJ3LZ/graph.json","fetch_events":"https://pith.science/api/pith-number/VK3VN63RNXZODHUHO6EFFUJ3LZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ/action/storage_attestation","attest_author":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ/action/author_attestation","sign_citation":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ/action/citation_signature","submit_replication":"https://pith.science/pith/VK3VN63RNXZODHUHO6EFFUJ3LZ/action/replication_record"}},"created_at":"2026-05-18T00:15:02.790849+00:00","updated_at":"2026-05-18T00:15:02.790849+00:00"}