{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:X7VV3ZPSVNUG43PA5KRDO2NYS7","short_pith_number":"pith:X7VV3ZPS","schema_version":"1.0","canonical_sha256":"bfeb5de5f2ab686e6de0eaa23769b897f162fa5047afc5f4f5da9181db7eded7","source":{"kind":"arxiv","id":"2106.03787","version":4},"attestation_state":"computed","paper":{"title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Julien P\\'erolat, Mathieu Lauri\\`ere, Matthieu Geist, Olivier Bachem, Olivier Pietquin, R\\'emi Munos, Romuald Elie, Sarah Perrin","submitted_at":"2021-06-07T16:51:07Z","abstract_excerpt":"Concave Utility Reinforcement Learning (CURL) extends RL from linear to concave utilities in the occupancy measure induced by the agent's policy. This encompasses not only RL but also imitation learning and exploration, among others. Yet, this more general paradigm invalidates the classical Bellman equations, and calls for new algorithms. Mean-field Games (MFGs) are a continuous approximation of many-agent RL. They consider the limit case of a continuous distribution of identical agents, anonymous with symmetric interests, and reduce the problem to the study of a single representative agent in"},"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":"2106.03787","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-07T16:51:07Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"10b3a3ada7ff8d9f478005a7a8fb1928f69dfe866bb899f8f39d25c41eed7bf4","abstract_canon_sha256":"03a87ac349524b6e2ea6ce80244aa023d8507b68bc91816dba70328e053da7eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:26.824940Z","signature_b64":"NYivhRkbb+LiW8+zJorhBYz3L4x8YTwys/knodIuVrpZJdNmpJ093JggZW6ckQNRs2ogaGNSf7s67y1Sjm/2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfeb5de5f2ab686e6de0eaa23769b897f162fa5047afc5f4f5da9181db7eded7","last_reissued_at":"2026-07-05T03:57:26.824477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:26.824477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Julien P\\'erolat, Mathieu Lauri\\`ere, Matthieu Geist, Olivier Bachem, Olivier Pietquin, R\\'emi Munos, Romuald Elie, Sarah Perrin","submitted_at":"2021-06-07T16:51:07Z","abstract_excerpt":"Concave Utility Reinforcement Learning (CURL) extends RL from linear to concave utilities in the occupancy measure induced by the agent's policy. This encompasses not only RL but also imitation learning and exploration, among others. Yet, this more general paradigm invalidates the classical Bellman equations, and calls for new algorithms. Mean-field Games (MFGs) are a continuous approximation of many-agent RL. They consider the limit case of a continuous distribution of identical agents, anonymous with symmetric interests, and reduce the problem to the study of a single representative agent in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03787","kind":"arxiv","version":4},"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/2106.03787/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":"2106.03787","created_at":"2026-07-05T03:57:26.824532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03787v4","created_at":"2026-07-05T03:57:26.824532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03787","created_at":"2026-07-05T03:57:26.824532+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7VV3ZPSVNUG","created_at":"2026-07-05T03:57:26.824532+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7VV3ZPSVNUG43PA","created_at":"2026-07-05T03:57:26.824532+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7VV3ZPS","created_at":"2026-07-05T03:57:26.824532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01432","citing_title":"The Geometry of Nonlinear Reinforcement Learning","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X7VV3ZPSVNUG43PA5KRDO2NYS7","json":"https://pith.science/pith/X7VV3ZPSVNUG43PA5KRDO2NYS7.json","graph_json":"https://pith.science/api/pith-number/X7VV3ZPSVNUG43PA5KRDO2NYS7/graph.json","events_json":"https://pith.science/api/pith-number/X7VV3ZPSVNUG43PA5KRDO2NYS7/events.json","paper":"https://pith.science/paper/X7VV3ZPS"},"agent_actions":{"view_html":"https://pith.science/pith/X7VV3ZPSVNUG43PA5KRDO2NYS7","download_json":"https://pith.science/pith/X7VV3ZPSVNUG43PA5KRDO2NYS7.json","view_paper":"https://pith.science/paper/X7VV3ZPS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03787&json=true","fetch_graph":"https://pith.science/api/pith-number/X7VV3ZPSVNUG43PA5KRDO2NYS7/graph.json","fetch_events":"https://pith.science/api/pith-number/X7VV3ZPSVNUG43PA5KRDO2NYS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7VV3ZPSVNUG43PA5KRDO2NYS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7VV3ZPSVNUG43PA5KRDO2NYS7/action/storage_attestation","attest_author":"https://pith.science/pith/X7VV3ZPSVNUG43PA5KRDO2NYS7/action/author_attestation","sign_citation":"https://pith.science/pith/X7VV3ZPSVNUG43PA5KRDO2NYS7/action/citation_signature","submit_replication":"https://pith.science/pith/X7VV3ZPSVNUG43PA5KRDO2NYS7/action/replication_record"}},"created_at":"2026-07-05T03:57:26.824532+00:00","updated_at":"2026-07-05T03:57:26.824532+00:00"}