{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:EUKYQP6ROKH6GXS7JJWYG5MFJN","short_pith_number":"pith:EUKYQP6R","schema_version":"1.0","canonical_sha256":"2515883fd1728fe35e5f4a6d8375854b64ef8db1d76134685da2120fdfef18a3","source":{"kind":"arxiv","id":"1101.0428","version":1},"attestation_state":"computed","paper":{"title":"The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eduardo Alonso, Michael Fairbank","submitted_at":"2011-01-02T20:20:27Z","abstract_excerpt":"In this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control problem in a large continuous state space. It is shown that learning the gradient of the value-function at every point along a trajectory generated by a greedy policy is a sufficient condition for the trajectory to be locally extremal, and often locally optimal, and we argue that this brings greater efficiency to value-function learning. This contrasts to traditional value-function learning in which the value-function must"},"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":"1101.0428","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-01-02T20:20:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"290763cccc2332f1644a43e6bc1352cfcfeb2c381b9a65c9041d1061572f2055","abstract_canon_sha256":"e035c8c2c89145420e9e4b6f07ede8c4640a68fead5775d25ba7805d4b7236d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:32:10.383858Z","signature_b64":"bX8s4Ndq8INdUdieCQUq5ijS+yJU380GRCB5L1jfC33jZ1gcnGQlUpJAv86U9gLK/cKMM9RR2jhNzXJML68/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2515883fd1728fe35e5f4a6d8375854b64ef8db1d76134685da2120fdfef18a3","last_reissued_at":"2026-05-18T04:32:10.383430Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:32:10.383430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eduardo Alonso, Michael Fairbank","submitted_at":"2011-01-02T20:20:27Z","abstract_excerpt":"In this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control problem in a large continuous state space. It is shown that learning the gradient of the value-function at every point along a trajectory generated by a greedy policy is a sufficient condition for the trajectory to be locally extremal, and often locally optimal, and we argue that this brings greater efficiency to value-function learning. This contrasts to traditional value-function learning in which the value-function must"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1101.0428","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":"1101.0428","created_at":"2026-05-18T04:32:10.383493+00:00"},{"alias_kind":"arxiv_version","alias_value":"1101.0428v1","created_at":"2026-05-18T04:32:10.383493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1101.0428","created_at":"2026-05-18T04:32:10.383493+00:00"},{"alias_kind":"pith_short_12","alias_value":"EUKYQP6ROKH6","created_at":"2026-05-18T12:26:28.662955+00:00"},{"alias_kind":"pith_short_16","alias_value":"EUKYQP6ROKH6GXS7","created_at":"2026-05-18T12:26:28.662955+00:00"},{"alias_kind":"pith_short_8","alias_value":"EUKYQP6R","created_at":"2026-05-18T12:26:28.662955+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/EUKYQP6ROKH6GXS7JJWYG5MFJN","json":"https://pith.science/pith/EUKYQP6ROKH6GXS7JJWYG5MFJN.json","graph_json":"https://pith.science/api/pith-number/EUKYQP6ROKH6GXS7JJWYG5MFJN/graph.json","events_json":"https://pith.science/api/pith-number/EUKYQP6ROKH6GXS7JJWYG5MFJN/events.json","paper":"https://pith.science/paper/EUKYQP6R"},"agent_actions":{"view_html":"https://pith.science/pith/EUKYQP6ROKH6GXS7JJWYG5MFJN","download_json":"https://pith.science/pith/EUKYQP6ROKH6GXS7JJWYG5MFJN.json","view_paper":"https://pith.science/paper/EUKYQP6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1101.0428&json=true","fetch_graph":"https://pith.science/api/pith-number/EUKYQP6ROKH6GXS7JJWYG5MFJN/graph.json","fetch_events":"https://pith.science/api/pith-number/EUKYQP6ROKH6GXS7JJWYG5MFJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EUKYQP6ROKH6GXS7JJWYG5MFJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EUKYQP6ROKH6GXS7JJWYG5MFJN/action/storage_attestation","attest_author":"https://pith.science/pith/EUKYQP6ROKH6GXS7JJWYG5MFJN/action/author_attestation","sign_citation":"https://pith.science/pith/EUKYQP6ROKH6GXS7JJWYG5MFJN/action/citation_signature","submit_replication":"https://pith.science/pith/EUKYQP6ROKH6GXS7JJWYG5MFJN/action/replication_record"}},"created_at":"2026-05-18T04:32:10.383493+00:00","updated_at":"2026-05-18T04:32:10.383493+00:00"}