{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FTYX7STMR3AQF3M2MUB6363TGF","short_pith_number":"pith:FTYX7STM","canonical_record":{"source":{"id":"2109.09717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T17:47:34Z","cross_cats_sorted":["cs.GT","cs.MA","math.OC"],"title_canon_sha256":"4be7b96a73545ddb11361c94f56f6811b2f1d309fc9fe9a241afdfc51bbcbda8","abstract_canon_sha256":"0000bc0929ec7a078e4ed31dba92df123a1e31cbb85b69641ad919f77f469557"},"schema_version":"1.0"},"canonical_sha256":"2cf17fca6c8ec102ed9a6503edfb73316fc0bffae283b2dbe169f82693cfc25c","source":{"kind":"arxiv","id":"2109.09717","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09717","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09717v1","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09717","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"pith_short_12","alias_value":"FTYX7STMR3AQ","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"pith_short_16","alias_value":"FTYX7STMR3AQF3M2","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"pith_short_8","alias_value":"FTYX7STM","created_at":"2026-07-05T03:15:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FTYX7STMR3AQF3M2MUB6363TGF","target":"record","payload":{"canonical_record":{"source":{"id":"2109.09717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T17:47:34Z","cross_cats_sorted":["cs.GT","cs.MA","math.OC"],"title_canon_sha256":"4be7b96a73545ddb11361c94f56f6811b2f1d309fc9fe9a241afdfc51bbcbda8","abstract_canon_sha256":"0000bc0929ec7a078e4ed31dba92df123a1e31cbb85b69641ad919f77f469557"},"schema_version":"1.0"},"canonical_sha256":"2cf17fca6c8ec102ed9a6503edfb73316fc0bffae283b2dbe169f82693cfc25c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:49.126168Z","signature_b64":"yY0GJPShZgYTjUNUT9RwS/1BRInexrQkJHOtg/Ujju9aHZKbZ7opBhpvz5KIXaL0FrON94rVhwYXWy852JAbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cf17fca6c8ec102ed9a6503edfb73316fc0bffae283b2dbe169f82693cfc25c","last_reissued_at":"2026-07-05T03:15:49.125691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:49.125691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.09717","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i4uE7wGHEdmigXgJz6WA7cvl3lbFrKnxPzJkcciTSZ6BMv72MOI8XMG1dcS47me7Kw0BSR6O0iun05KQzS6bCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:32:23.752426Z"},"content_sha256":"7483d6509ccdceecb4a51af212d4810f86b7ba502e9856765f58d8864e70abbc","schema_version":"1.0","event_id":"sha256:7483d6509ccdceecb4a51af212d4810f86b7ba502e9856765f58d8864e70abbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FTYX7STMR3AQF3M2MUB6363TGF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalization in Mean Field Games by Learning Master Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT","cs.MA","math.OC"],"primary_cat":"cs.LG","authors_text":"Julien P\\'erolat, Mathieu Lauri\\`ere, Matthieu Geist, Olivier Pietquin, Romuald \\'Elie, Sarah Perrin","submitted_at":"2021-09-20T17:47:34Z","abstract_excerpt":"Mean Field Games (MFGs) can potentially scale multi-agent systems to extremely large populations of agents. Yet, most of the literature assumes a single initial distribution for the agents, which limits the practical applications of MFGs. Machine Learning has the potential to solve a wider diversity of MFG problems thanks to generalizations capacities. We study how to leverage these generalization properties to learn policies enabling a typical agent to behave optimally against any population distribution. In reference to the Master equation in MFGs, we coin the term ``Master policies'' to des"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09717","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/2109.09717/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"An9kQRObV6u6917BZFx1EvLlwnCMeu2y7rKjnrGJuQ6Z0oWDIF5vQ1bVvm86CfA7NXKZJRRcbW50663N0MdrDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T12:32:23.753103Z"},"content_sha256":"31af39339494b1bfa81ccc1c05a9a0ab5b67d4c380fe89f62f5fb62c4947b0b3","schema_version":"1.0","event_id":"sha256:31af39339494b1bfa81ccc1c05a9a0ab5b67d4c380fe89f62f5fb62c4947b0b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FTYX7STMR3AQF3M2MUB6363TGF/bundle.json","state_url":"https://pith.science/pith/FTYX7STMR3AQF3M2MUB6363TGF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FTYX7STMR3AQF3M2MUB6363TGF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-05T12:32:23Z","links":{"resolver":"https://pith.science/pith/FTYX7STMR3AQF3M2MUB6363TGF","bundle":"https://pith.science/pith/FTYX7STMR3AQF3M2MUB6363TGF/bundle.json","state":"https://pith.science/pith/FTYX7STMR3AQF3M2MUB6363TGF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FTYX7STMR3AQF3M2MUB6363TGF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FTYX7STMR3AQF3M2MUB6363TGF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0000bc0929ec7a078e4ed31dba92df123a1e31cbb85b69641ad919f77f469557","cross_cats_sorted":["cs.GT","cs.MA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T17:47:34Z","title_canon_sha256":"4be7b96a73545ddb11361c94f56f6811b2f1d309fc9fe9a241afdfc51bbcbda8"},"schema_version":"1.0","source":{"id":"2109.09717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09717","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09717v1","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09717","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"pith_short_12","alias_value":"FTYX7STMR3AQ","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"pith_short_16","alias_value":"FTYX7STMR3AQF3M2","created_at":"2026-07-05T03:15:49Z"},{"alias_kind":"pith_short_8","alias_value":"FTYX7STM","created_at":"2026-07-05T03:15:49Z"}],"graph_snapshots":[{"event_id":"sha256:31af39339494b1bfa81ccc1c05a9a0ab5b67d4c380fe89f62f5fb62c4947b0b3","target":"graph","created_at":"2026-07-05T03:15:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.09717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mean Field Games (MFGs) can potentially scale multi-agent systems to extremely large populations of agents. Yet, most of the literature assumes a single initial distribution for the agents, which limits the practical applications of MFGs. Machine Learning has the potential to solve a wider diversity of MFG problems thanks to generalizations capacities. We study how to leverage these generalization properties to learn policies enabling a typical agent to behave optimally against any population distribution. In reference to the Master equation in MFGs, we coin the term ``Master policies'' to des","authors_text":"Julien P\\'erolat, Mathieu Lauri\\`ere, Matthieu Geist, Olivier Pietquin, Romuald \\'Elie, Sarah Perrin","cross_cats":["cs.GT","cs.MA","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T17:47:34Z","title":"Generalization in Mean Field Games by Learning Master Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09717","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7483d6509ccdceecb4a51af212d4810f86b7ba502e9856765f58d8864e70abbc","target":"record","created_at":"2026-07-05T03:15:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0000bc0929ec7a078e4ed31dba92df123a1e31cbb85b69641ad919f77f469557","cross_cats_sorted":["cs.GT","cs.MA","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T17:47:34Z","title_canon_sha256":"4be7b96a73545ddb11361c94f56f6811b2f1d309fc9fe9a241afdfc51bbcbda8"},"schema_version":"1.0","source":{"id":"2109.09717","kind":"arxiv","version":1}},"canonical_sha256":"2cf17fca6c8ec102ed9a6503edfb73316fc0bffae283b2dbe169f82693cfc25c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cf17fca6c8ec102ed9a6503edfb73316fc0bffae283b2dbe169f82693cfc25c","first_computed_at":"2026-07-05T03:15:49.125691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:49.125691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yY0GJPShZgYTjUNUT9RwS/1BRInexrQkJHOtg/Ujju9aHZKbZ7opBhpvz5KIXaL0FrON94rVhwYXWy852JAbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:49.126168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.09717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7483d6509ccdceecb4a51af212d4810f86b7ba502e9856765f58d8864e70abbc","sha256:31af39339494b1bfa81ccc1c05a9a0ab5b67d4c380fe89f62f5fb62c4947b0b3"],"state_sha256":"b0cf3aacd865e9f2cfcee8d56d1888c78e9656ed8df1c1d6bd3974b36c28448c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8XYsgE8U/WuP4JOVwEQpAL3pA19FZz339ikYWBVu1770g9ZnHsSh3BmWmhxTh5BdWpt8kxHP8fjiLy7fzJTYDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T12:32:23.756070Z","bundle_sha256":"aeac26debae41fc3a6c7dfb75a1cf72bcbecf993953db4741b72cd74ad11bd69"}}