{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NFQB5SRKRU4FCLV7MAH7H37TBO","short_pith_number":"pith:NFQB5SRK","schema_version":"1.0","canonical_sha256":"69601eca2a8d38512ebf600ff3eff30b87612f153e004ff32437842fcdfcb810","source":{"kind":"arxiv","id":"2203.01500","version":1},"attestation_state":"computed","paper":{"title":"The Dynamics of Q-learning in Population Games: a Physics-Inspired Continuity Equation Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Chin-wing Leung, Harold Soh, Ho-fung Leung, Shuyue Hu","submitted_at":"2022-03-03T03:22:38Z","abstract_excerpt":"Although learning has found wide application in multi-agent systems, its effects on the temporal evolution of a system are far from understood. This paper focuses on the dynamics of Q-learning in large-scale multi-agent systems modeled as population games. We revisit the replicator equation model for Q-learning dynamics and observe that this model is inappropriate for our concerned setting. Motivated by this, we develop a new formal model, which bears a formal connection with the continuity equation in physics. We show that our model always accurately describes the Q-learning dynamics in popul"},"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":"2203.01500","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2022-03-03T03:22:38Z","cross_cats_sorted":[],"title_canon_sha256":"3fb6d3b93932b908d5c50dd18f9ce500eac1ebfcb558f0878f068cd47ea66c79","abstract_canon_sha256":"6f80d7abf450b8ee566accc9b227d8cda561794981d0a88f6a3b0757ee6a7cee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:48.576056Z","signature_b64":"uWxAWJFoQLZYeo/aukwNpx8qnX86DKMGj2yBGXEXJ47JQjhytJwojJ0ZBeU5dFLviirf6bt7D+wfY4Traq6PAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69601eca2a8d38512ebf600ff3eff30b87612f153e004ff32437842fcdfcb810","last_reissued_at":"2026-07-05T04:01:48.575559Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:48.575559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Dynamics of Q-learning in Population Games: a Physics-Inspired Continuity Equation Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Chin-wing Leung, Harold Soh, Ho-fung Leung, Shuyue Hu","submitted_at":"2022-03-03T03:22:38Z","abstract_excerpt":"Although learning has found wide application in multi-agent systems, its effects on the temporal evolution of a system are far from understood. This paper focuses on the dynamics of Q-learning in large-scale multi-agent systems modeled as population games. We revisit the replicator equation model for Q-learning dynamics and observe that this model is inappropriate for our concerned setting. Motivated by this, we develop a new formal model, which bears a formal connection with the continuity equation in physics. We show that our model always accurately describes the Q-learning dynamics in popul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01500","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/2203.01500/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":"2203.01500","created_at":"2026-07-05T04:01:48.575631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.01500v1","created_at":"2026-07-05T04:01:48.575631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01500","created_at":"2026-07-05T04:01:48.575631+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFQB5SRKRU4F","created_at":"2026-07-05T04:01:48.575631+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFQB5SRKRU4FCLV7","created_at":"2026-07-05T04:01:48.575631+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFQB5SRK","created_at":"2026-07-05T04:01:48.575631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18185","citing_title":"The Dynamics of Policy Gradient in Social Dilemmas with Partner Selection","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18185","citing_title":"The Dynamics of Policy Gradient in Social Dilemmas with Partner Selection","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFQB5SRKRU4FCLV7MAH7H37TBO","json":"https://pith.science/pith/NFQB5SRKRU4FCLV7MAH7H37TBO.json","graph_json":"https://pith.science/api/pith-number/NFQB5SRKRU4FCLV7MAH7H37TBO/graph.json","events_json":"https://pith.science/api/pith-number/NFQB5SRKRU4FCLV7MAH7H37TBO/events.json","paper":"https://pith.science/paper/NFQB5SRK"},"agent_actions":{"view_html":"https://pith.science/pith/NFQB5SRKRU4FCLV7MAH7H37TBO","download_json":"https://pith.science/pith/NFQB5SRKRU4FCLV7MAH7H37TBO.json","view_paper":"https://pith.science/paper/NFQB5SRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.01500&json=true","fetch_graph":"https://pith.science/api/pith-number/NFQB5SRKRU4FCLV7MAH7H37TBO/graph.json","fetch_events":"https://pith.science/api/pith-number/NFQB5SRKRU4FCLV7MAH7H37TBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFQB5SRKRU4FCLV7MAH7H37TBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFQB5SRKRU4FCLV7MAH7H37TBO/action/storage_attestation","attest_author":"https://pith.science/pith/NFQB5SRKRU4FCLV7MAH7H37TBO/action/author_attestation","sign_citation":"https://pith.science/pith/NFQB5SRKRU4FCLV7MAH7H37TBO/action/citation_signature","submit_replication":"https://pith.science/pith/NFQB5SRKRU4FCLV7MAH7H37TBO/action/replication_record"}},"created_at":"2026-07-05T04:01:48.575631+00:00","updated_at":"2026-07-05T04:01:48.575631+00:00"}