{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F5YQUPEDZC34W73XKMHWW5XCF2","short_pith_number":"pith:F5YQUPED","schema_version":"1.0","canonical_sha256":"2f710a3c83c8b7cb7f77530f6b76e22eb57fa5fc8d5ac237ed2f5ce283413c91","source":{"kind":"arxiv","id":"2403.03552","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.03552","created_at":"2026-07-05T07:52:49.852999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03552v1","created_at":"2026-07-05T07:52:49.852999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03552","created_at":"2026-07-05T07:52:49.852999+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5YQUPEDZC34","created_at":"2026-07-05T07:52:49.852999+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5YQUPEDZC34W73X","created_at":"2026-07-05T07:52:49.852999+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5YQUPED","created_at":"2026-07-05T07:52:49.852999+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11042","citing_title":"Towards Model-Free Learning in Dynamic Population Games: An Application to Karma Economies","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2","json":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2.json","graph_json":"https://pith.science/api/pith-number/F5YQUPEDZC34W73XKMHWW5XCF2/graph.json","events_json":"https://pith.science/api/pith-number/F5YQUPEDZC34W73XKMHWW5XCF2/events.json","paper":"https://pith.science/paper/F5YQUPED"},"agent_actions":{"view_html":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2","download_json":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2.json","view_paper":"https://pith.science/paper/F5YQUPED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03552&json=true","fetch_graph":"https://pith.science/api/pith-number/F5YQUPEDZC34W73XKMHWW5XCF2/graph.json","fetch_events":"https://pith.science/api/pith-number/F5YQUPEDZC34W73XKMHWW5XCF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2/action/storage_attestation","attest_author":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2/action/author_attestation","sign_citation":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2/action/citation_signature","submit_replication":"https://pith.science/pith/F5YQUPEDZC34W73XKMHWW5XCF2/action/replication_record"}},"created_at":"2026-07-05T07:52:49.852999+00:00","updated_at":"2026-07-05T07:52:49.852999+00:00"}