{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F5YQUPEDZC34W73XKMHWW5XCF2","short_pith_number":"pith:F5YQUPED","canonical_record":{"source":{"id":"2403.03552","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2024-03-06T08:55:34Z","cross_cats_sorted":["cs.LG","cs.MA","cs.SY","eess.SY"],"title_canon_sha256":"9e2d718669dae7d4b4151c00ece23201e47a8fb49c752f589f44d641e9a18e58","abstract_canon_sha256":"1894e4b7abee301a70ca2f884654da3f085aea3c4e3618b5b60e71a9ae8b728b"},"schema_version":"1.0"},"canonical_sha256":"2f710a3c83c8b7cb7f77530f6b76e22eb57fa5fc8d5ac237ed2f5ce283413c91","source":{"kind":"arxiv","id":"2403.03552","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03552","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03552v1","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03552","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"F5YQUPEDZC34","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"pith_short_16","alias_value":"F5YQUPEDZC34W73X","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"pith_short_8","alias_value":"F5YQUPED","created_at":"2026-07-05T07:52:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F5YQUPEDZC34W73XKMHWW5XCF2","target":"record","payload":{"canonical_record":{"source":{"id":"2403.03552","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2024-03-06T08:55:34Z","cross_cats_sorted":["cs.LG","cs.MA","cs.SY","eess.SY"],"title_canon_sha256":"9e2d718669dae7d4b4151c00ece23201e47a8fb49c752f589f44d641e9a18e58","abstract_canon_sha256":"1894e4b7abee301a70ca2f884654da3f085aea3c4e3618b5b60e71a9ae8b728b"},"schema_version":"1.0"},"canonical_sha256":"2f710a3c83c8b7cb7f77530f6b76e22eb57fa5fc8d5ac237ed2f5ce283413c91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:49.853334Z","signature_b64":"yKiYjzw/xpWqCxtHMx2vYQSERwnh2Ih7cNYYenXvzBLymU9fL8AOjsdwlJV31kRMjS68/fQnD0TeIz1YutpTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f710a3c83c8b7cb7f77530f6b76e22eb57fa5fc8d5ac237ed2f5ce283413c91","last_reissued_at":"2026-07-05T07:52:49.852930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:49.852930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.03552","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":"2026-07-05T07:52:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IGHj/hMZyOPjO+k+1VOkbfSC3qnWjbtTJlOjseLZvmfHto3+vlRre4mv9KpUhjtU3JvA1jRn1o/qc/NFcqb+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:45:37.044345Z"},"content_sha256":"aedeb2a1218ed0b9672e16e81d677dbbcc074c6b0012b72160c17133c872760b","schema_version":"1.0","event_id":"sha256:aedeb2a1218ed0b9672e16e81d677dbbcc074c6b0012b72160c17133c872760b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F5YQUPEDZC34W73XKMHWW5XCF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MA","cs.SY","eess.SY"],"primary_cat":"cs.GT","authors_text":"Ankur Mehta, Mathieu Lauriere, Matthieu Geist, Olivier Pietquin, Samuel Jia Cong Chua, Zida Wu","submitted_at":"2024-03-06T08:55:34Z","abstract_excerpt":"Mean Field Games (MFGs) have the ability to handle large-scale multi-agent systems, but learning Nash equilibria in MFGs remains a challenging task. In this paper, we propose a deep reinforcement learning (DRL) algorithm that achieves population-dependent Nash equilibrium without the need for averaging or sampling from history, inspired by Munchausen RL and Online Mirror Descent. Through the design of an additional inner-loop replay buffer, the agents can effectively learn to achieve Nash equilibrium from any distribution, mitigating catastrophic forgetting. The resulting policy can be applied"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03552","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/2403.03552/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":"2026-07-05T07:52:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V7SKJ6ShT5xgOCIOi1q3LGthb32Wnsk+LV9aYhpbnCCP/uP/yxY2DW7znULwUJFVPSmyYoCBkUur9muTEVteCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:45:37.047308Z"},"content_sha256":"e6acd5a3aef795f28bd253fee38bc6e9763225431693b92ab3947dd77c73fd15","schema_version":"1.0","event_id":"sha256:e6acd5a3aef795f28bd253fee38bc6e9763225431693b92ab3947dd77c73fd15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2/bundle.json","state_url":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5YQUPEDZC34W73XKMHWW5XCF2/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":"2026-08-18T18:45:37Z","links":{"resolver":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2","bundle":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2/bundle.json","state":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5YQUPEDZC34W73XKMHWW5XCF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F5YQUPEDZC34W73XKMHWW5XCF2","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":"1894e4b7abee301a70ca2f884654da3f085aea3c4e3618b5b60e71a9ae8b728b","cross_cats_sorted":["cs.LG","cs.MA","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2024-03-06T08:55:34Z","title_canon_sha256":"9e2d718669dae7d4b4151c00ece23201e47a8fb49c752f589f44d641e9a18e58"},"schema_version":"1.0","source":{"id":"2403.03552","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03552","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03552v1","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03552","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"F5YQUPEDZC34","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"pith_short_16","alias_value":"F5YQUPEDZC34W73X","created_at":"2026-07-05T07:52:49Z"},{"alias_kind":"pith_short_8","alias_value":"F5YQUPED","created_at":"2026-07-05T07:52:49Z"}],"graph_snapshots":[{"event_id":"sha256:e6acd5a3aef795f28bd253fee38bc6e9763225431693b92ab3947dd77c73fd15","target":"graph","created_at":"2026-07-05T07:52:49Z","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/2403.03552/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mean Field Games (MFGs) have the ability to handle large-scale multi-agent systems, but learning Nash equilibria in MFGs remains a challenging task. In this paper, we propose a deep reinforcement learning (DRL) algorithm that achieves population-dependent Nash equilibrium without the need for averaging or sampling from history, inspired by Munchausen RL and Online Mirror Descent. Through the design of an additional inner-loop replay buffer, the agents can effectively learn to achieve Nash equilibrium from any distribution, mitigating catastrophic forgetting. The resulting policy can be applied","authors_text":"Ankur Mehta, Mathieu Lauriere, Matthieu Geist, Olivier Pietquin, Samuel Jia Cong Chua, Zida Wu","cross_cats":["cs.LG","cs.MA","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2024-03-06T08:55:34Z","title":"Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03552","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:aedeb2a1218ed0b9672e16e81d677dbbcc074c6b0012b72160c17133c872760b","target":"record","created_at":"2026-07-05T07:52:49Z","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":"1894e4b7abee301a70ca2f884654da3f085aea3c4e3618b5b60e71a9ae8b728b","cross_cats_sorted":["cs.LG","cs.MA","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2024-03-06T08:55:34Z","title_canon_sha256":"9e2d718669dae7d4b4151c00ece23201e47a8fb49c752f589f44d641e9a18e58"},"schema_version":"1.0","source":{"id":"2403.03552","kind":"arxiv","version":1}},"canonical_sha256":"2f710a3c83c8b7cb7f77530f6b76e22eb57fa5fc8d5ac237ed2f5ce283413c91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f710a3c83c8b7cb7f77530f6b76e22eb57fa5fc8d5ac237ed2f5ce283413c91","first_computed_at":"2026-07-05T07:52:49.852930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:49.852930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yKiYjzw/xpWqCxtHMx2vYQSERwnh2Ih7cNYYenXvzBLymU9fL8AOjsdwlJV31kRMjS68/fQnD0TeIz1YutpTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:49.853334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03552","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aedeb2a1218ed0b9672e16e81d677dbbcc074c6b0012b72160c17133c872760b","sha256:e6acd5a3aef795f28bd253fee38bc6e9763225431693b92ab3947dd77c73fd15"],"state_sha256":"e9fd44f6d04c6960a8e4e7fe68b7996404b8810fafdd4f9d66c04069adff5aaf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b9/9rTqeqME9v1b+WoOoH9oF88gt95aVcf+ygKPlg31c8GUaK+C8ICaYOf49ex9A1wOXcOfs30wQ/1KvhPhxBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:45:37.055879Z","bundle_sha256":"0c6593e465b518347b32c80d7477066c5e8ea96de7ebff027a9a305a729e8f42"}}