{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UX2V6BZ2RTN3B3QVEXJNCRJK3K","short_pith_number":"pith:UX2V6BZ2","canonical_record":{"source":{"id":"2006.13912","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-24T17:45:44Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"a3fe134ea2c58c2e635f127efda89937d54b48c86ce61d8cd96cbfdea122b928","abstract_canon_sha256":"bc760142b4533904868a68310b0dae1c224c6838c392b73199a7198399f50a45"},"schema_version":"1.0"},"canonical_sha256":"a5f55f073a8cdbb0ee1525d2d1452adaa415a3de570ba0a8b1cd403269d2d6f0","source":{"kind":"arxiv","id":"2006.13912","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13912","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13912v3","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13912","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_12","alias_value":"UX2V6BZ2RTN3","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_16","alias_value":"UX2V6BZ2RTN3B3QV","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_8","alias_value":"UX2V6BZ2","created_at":"2026-07-05T02:44:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UX2V6BZ2RTN3B3QVEXJNCRJK3K","target":"record","payload":{"canonical_record":{"source":{"id":"2006.13912","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-24T17:45:44Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"a3fe134ea2c58c2e635f127efda89937d54b48c86ce61d8cd96cbfdea122b928","abstract_canon_sha256":"bc760142b4533904868a68310b0dae1c224c6838c392b73199a7198399f50a45"},"schema_version":"1.0"},"canonical_sha256":"a5f55f073a8cdbb0ee1525d2d1452adaa415a3de570ba0a8b1cd403269d2d6f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:32.893575Z","signature_b64":"yDhf6xl9HGAN7LTW7ageECnfwA3SzjDtXdeU9ul1z4K0zQ6McrX1ka//IW5JmB3Vt03YSXrba1UFlt3fA/jrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5f55f073a8cdbb0ee1525d2d1452adaa415a3de570ba0a8b1cd403269d2d6f0","last_reissued_at":"2026-07-05T02:44:32.893093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:32.893093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.13912","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:44:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BB5tafQYCQzpdArn8wcGwHnliJbsezN67fP3WtBG9UmqFDrJl/IBOSqTPuLh8HtiXG50soccTF/NPKdoht+qAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:43:31.877776Z"},"content_sha256":"0a77d701ae60829bbdb694f6224988b2e705c390750099d6f8f3643233ba7506","schema_version":"1.0","event_id":"sha256:0a77d701ae60829bbdb694f6224988b2e705c390750099d6f8f3643233ba7506"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UX2V6BZ2RTN3B3QVEXJNCRJK3K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Reinforcement Q-Learning for Mean Field Game and Control Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"math.OC","authors_text":"Andrea Angiuli, Jean-Pierre Fouque, Mathieu Lauri\\`ere","submitted_at":"2020-06-24T17:45:44Z","abstract_excerpt":"We present a Reinforcement Learning (RL) algorithm to solve infinite horizon asymptotic Mean Field Game (MFG) and Mean Field Control (MFC) problems. Our approach can be described as a unified two-timescale Mean Field Q-learning: The \\emph{same} algorithm can learn either the MFG or the MFC solution by simply tuning the ratio of two learning parameters. The algorithm is in discrete time and space where the agent not only provides an action to the environment but also a distribution of the state in order to take into account the mean field feature of the problem. Importantly, we assume that the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13912","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.13912/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":"2026-07-05T02:44:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CgCAL0Ff0NmX0LwOqR4TQywzh8th3k1/p8kxFvm2kZ56RkiuiZSW4mtn1KMhWoLzsP68FvIsSVTir0qG3DzIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:43:31.878308Z"},"content_sha256":"8f4f3f43f02b79c04e5c81dc3129263270ce8c36a61afd308d6d0502bd296b7f","schema_version":"1.0","event_id":"sha256:8f4f3f43f02b79c04e5c81dc3129263270ce8c36a61afd308d6d0502bd296b7f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UX2V6BZ2RTN3B3QVEXJNCRJK3K/bundle.json","state_url":"https://pith.science/pith/UX2V6BZ2RTN3B3QVEXJNCRJK3K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UX2V6BZ2RTN3B3QVEXJNCRJK3K/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":"2026-08-09T19:43:31Z","links":{"resolver":"https://pith.science/pith/UX2V6BZ2RTN3B3QVEXJNCRJK3K","bundle":"https://pith.science/pith/UX2V6BZ2RTN3B3QVEXJNCRJK3K/bundle.json","state":"https://pith.science/pith/UX2V6BZ2RTN3B3QVEXJNCRJK3K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UX2V6BZ2RTN3B3QVEXJNCRJK3K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UX2V6BZ2RTN3B3QVEXJNCRJK3K","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":"bc760142b4533904868a68310b0dae1c224c6838c392b73199a7198399f50a45","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-24T17:45:44Z","title_canon_sha256":"a3fe134ea2c58c2e635f127efda89937d54b48c86ce61d8cd96cbfdea122b928"},"schema_version":"1.0","source":{"id":"2006.13912","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13912","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13912v3","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13912","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_12","alias_value":"UX2V6BZ2RTN3","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_16","alias_value":"UX2V6BZ2RTN3B3QV","created_at":"2026-07-05T02:44:32Z"},{"alias_kind":"pith_short_8","alias_value":"UX2V6BZ2","created_at":"2026-07-05T02:44:32Z"}],"graph_snapshots":[{"event_id":"sha256:8f4f3f43f02b79c04e5c81dc3129263270ce8c36a61afd308d6d0502bd296b7f","target":"graph","created_at":"2026-07-05T02:44:32Z","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/2006.13912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a Reinforcement Learning (RL) algorithm to solve infinite horizon asymptotic Mean Field Game (MFG) and Mean Field Control (MFC) problems. Our approach can be described as a unified two-timescale Mean Field Q-learning: The \\emph{same} algorithm can learn either the MFG or the MFC solution by simply tuning the ratio of two learning parameters. The algorithm is in discrete time and space where the agent not only provides an action to the environment but also a distribution of the state in order to take into account the mean field feature of the problem. Importantly, we assume that the ","authors_text":"Andrea Angiuli, Jean-Pierre Fouque, Mathieu Lauri\\`ere","cross_cats":["cs.LG","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-24T17:45:44Z","title":"Unified Reinforcement Q-Learning for Mean Field Game and Control Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13912","kind":"arxiv","version":3},"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":"sha256:0a77d701ae60829bbdb694f6224988b2e705c390750099d6f8f3643233ba7506","target":"record","created_at":"2026-07-05T02:44:32Z","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":"bc760142b4533904868a68310b0dae1c224c6838c392b73199a7198399f50a45","cross_cats_sorted":["cs.LG","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-06-24T17:45:44Z","title_canon_sha256":"a3fe134ea2c58c2e635f127efda89937d54b48c86ce61d8cd96cbfdea122b928"},"schema_version":"1.0","source":{"id":"2006.13912","kind":"arxiv","version":3}},"canonical_sha256":"a5f55f073a8cdbb0ee1525d2d1452adaa415a3de570ba0a8b1cd403269d2d6f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a5f55f073a8cdbb0ee1525d2d1452adaa415a3de570ba0a8b1cd403269d2d6f0","first_computed_at":"2026-07-05T02:44:32.893093Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:32.893093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yDhf6xl9HGAN7LTW7ageECnfwA3SzjDtXdeU9ul1z4K0zQ6McrX1ka//IW5JmB3Vt03YSXrba1UFlt3fA/jrDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:32.893575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.13912","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a77d701ae60829bbdb694f6224988b2e705c390750099d6f8f3643233ba7506","sha256:8f4f3f43f02b79c04e5c81dc3129263270ce8c36a61afd308d6d0502bd296b7f"],"state_sha256":"4eb707d62e8b1b4438c6daccc15d7165ad113307bd683bb137bfe0bffd311a88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lLKosp7oFrJq3i/A6g3/uvGhpg77QLeMv5YsLTrk/lOvNwyjIE5hp1lci0XYHDGJ1aQgkLLJrJU0FqwOTNgFAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:43:31.884457Z","bundle_sha256":"0e9227792b9338ced310ab34074fe4e483780f8e59fec0df19f9e58bcdc59550"}}