{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:ORUGAEGN6HB6JEO6I2TFQLOVVA","short_pith_number":"pith:ORUGAEGN","schema_version":"1.0","canonical_sha256":"74686010cdf1c3e491de46a6582dd5a8007091d727a617092f85a4ad27c2e64b","source":{"kind":"arxiv","id":"1004.2342","version":3},"attestation_state":"computed","paper":{"title":"Mean field for Markov Decision Processes: from Discrete to Continuous Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF","cs.SY","math.OC","math.PR"],"primary_cat":"cs.AI","authors_text":"Bruno Gaujal (INRIA Grenoble Rh\\^one-Alpes / LIG laboratoire d'Informatique de Grenoble), EPFL), Jean-Yves Le Boudec (EPFL), Nicolas Gast (INRIA Grenoble Rh\\^one-Alpes / LIG laboratoire d'Informatique de Grenoble","submitted_at":"2010-04-14T07:56:40Z","abstract_excerpt":"We study the convergence of Markov Decision Processes made of a large number of objects to optimization problems on ordinary differential equations (ODE). We show that the optimal reward of such a Markov Decision Process, satisfying a Bellman equation, converges to the solution of a continuous Hamilton-Jacobi-Bellman (HJB) equation based on the mean field approximation of the Markov Decision Process. We give bounds on the difference of the rewards, and a constructive algorithm for deriving an approximating solution to the Markov Decision Process from a solution of the HJB equations. We illustr"},"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":"1004.2342","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2010-04-14T07:56:40Z","cross_cats_sorted":["cs.PF","cs.SY","math.OC","math.PR"],"title_canon_sha256":"9de6fce638c90cfff8cce321f7a7312f02d4f990d0d88c35ec271d05d7481b51","abstract_canon_sha256":"264683f0d5f9b86aceb03ca282df56e8766d44966e7e203ca05e1598f13d816c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:21:51.748060Z","signature_b64":"mXqbvXflZOBUGIVDlKB7VXBEyCrjiMAfSz6rI4CChIHFbiOmPjvYPGYbhFQOF/cIbjwG55nUjekVeidpdmS3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74686010cdf1c3e491de46a6582dd5a8007091d727a617092f85a4ad27c2e64b","last_reissued_at":"2026-05-18T04:21:51.747368Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:21:51.747368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mean field for Markov Decision Processes: from Discrete to Continuous Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF","cs.SY","math.OC","math.PR"],"primary_cat":"cs.AI","authors_text":"Bruno Gaujal (INRIA Grenoble Rh\\^one-Alpes / LIG laboratoire d'Informatique de Grenoble), EPFL), Jean-Yves Le Boudec (EPFL), Nicolas Gast (INRIA Grenoble Rh\\^one-Alpes / LIG laboratoire d'Informatique de Grenoble","submitted_at":"2010-04-14T07:56:40Z","abstract_excerpt":"We study the convergence of Markov Decision Processes made of a large number of objects to optimization problems on ordinary differential equations (ODE). We show that the optimal reward of such a Markov Decision Process, satisfying a Bellman equation, converges to the solution of a continuous Hamilton-Jacobi-Bellman (HJB) equation based on the mean field approximation of the Markov Decision Process. We give bounds on the difference of the rewards, and a constructive algorithm for deriving an approximating solution to the Markov Decision Process from a solution of the HJB equations. We illustr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1004.2342","kind":"arxiv","version":3},"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":"1004.2342","created_at":"2026-05-18T04:21:51.747466+00:00"},{"alias_kind":"arxiv_version","alias_value":"1004.2342v3","created_at":"2026-05-18T04:21:51.747466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1004.2342","created_at":"2026-05-18T04:21:51.747466+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORUGAEGN6HB6","created_at":"2026-05-18T12:26:12.377268+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORUGAEGN6HB6JEO6","created_at":"2026-05-18T12:26:12.377268+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORUGAEGN","created_at":"2026-05-18T12:26:12.377268+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/ORUGAEGN6HB6JEO6I2TFQLOVVA","json":"https://pith.science/pith/ORUGAEGN6HB6JEO6I2TFQLOVVA.json","graph_json":"https://pith.science/api/pith-number/ORUGAEGN6HB6JEO6I2TFQLOVVA/graph.json","events_json":"https://pith.science/api/pith-number/ORUGAEGN6HB6JEO6I2TFQLOVVA/events.json","paper":"https://pith.science/paper/ORUGAEGN"},"agent_actions":{"view_html":"https://pith.science/pith/ORUGAEGN6HB6JEO6I2TFQLOVVA","download_json":"https://pith.science/pith/ORUGAEGN6HB6JEO6I2TFQLOVVA.json","view_paper":"https://pith.science/paper/ORUGAEGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1004.2342&json=true","fetch_graph":"https://pith.science/api/pith-number/ORUGAEGN6HB6JEO6I2TFQLOVVA/graph.json","fetch_events":"https://pith.science/api/pith-number/ORUGAEGN6HB6JEO6I2TFQLOVVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORUGAEGN6HB6JEO6I2TFQLOVVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORUGAEGN6HB6JEO6I2TFQLOVVA/action/storage_attestation","attest_author":"https://pith.science/pith/ORUGAEGN6HB6JEO6I2TFQLOVVA/action/author_attestation","sign_citation":"https://pith.science/pith/ORUGAEGN6HB6JEO6I2TFQLOVVA/action/citation_signature","submit_replication":"https://pith.science/pith/ORUGAEGN6HB6JEO6I2TFQLOVVA/action/replication_record"}},"created_at":"2026-05-18T04:21:51.747466+00:00","updated_at":"2026-05-18T04:21:51.747466+00:00"}