{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:PVS73NEUOUKID5L6OJAGBTDEOC","short_pith_number":"pith:PVS73NEU","schema_version":"1.0","canonical_sha256":"7d65fdb494751481f57e724060cc6470a81ba69acbaf6d6c70326abfba46a323","source":{"kind":"arxiv","id":"1809.03066","version":3},"attestation_state":"computed","paper":{"title":"Multi-agent online learning in time-varying games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"cs.GT","authors_text":"Benoit Duvocelle, Dries Vermeulen, Mathias Staudigl, Panayotis Mertikopoulos","submitted_at":"2018-09-10T00:23:25Z","abstract_excerpt":"We examine the long-run behavior of multi-agent online learning in games that evolve over time. Specifically, we focus on a wide class of policies based on mirror descent, and we show that the induced sequence of play (a) converges to Nash equilibrium in time-varying games that stabilize in the long run to a strictly monotone limit; and (b) it stays asymptotically close to the evolving equilibrium of the sequence of stage games (assuming they are strongly monotone). Our results apply to both gradient-based and payoff-based feedback - i.e., the \"bandit feedback\" case where players only get to o"},"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":"1809.03066","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2018-09-10T00:23:25Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"77f7199823cf24f538199eb25d09e4e445d40d520e23b4239a86c2baa7aac434","abstract_canon_sha256":"fc53c30f99414a581ff816831f3ec460637251cf26bc4eeb12e68acf1da243c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:47:20.956477Z","signature_b64":"ImzqtebtumP8BEhoWJ91HoqYPPxANAeYphBr5YYgPVlMrpWElmr4dZ4mY5SoXTujbxm3y/HImMyX7FHoJIeqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d65fdb494751481f57e724060cc6470a81ba69acbaf6d6c70326abfba46a323","last_reissued_at":"2026-07-05T04:47:20.956035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:47:20.956035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-agent online learning in time-varying games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"cs.GT","authors_text":"Benoit Duvocelle, Dries Vermeulen, Mathias Staudigl, Panayotis Mertikopoulos","submitted_at":"2018-09-10T00:23:25Z","abstract_excerpt":"We examine the long-run behavior of multi-agent online learning in games that evolve over time. Specifically, we focus on a wide class of policies based on mirror descent, and we show that the induced sequence of play (a) converges to Nash equilibrium in time-varying games that stabilize in the long run to a strictly monotone limit; and (b) it stays asymptotically close to the evolving equilibrium of the sequence of stage games (assuming they are strongly monotone). Our results apply to both gradient-based and payoff-based feedback - i.e., the \"bandit feedback\" case where players only get to o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03066","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/1809.03066/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":"1809.03066","created_at":"2026-07-05T04:47:20.956092+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.03066v3","created_at":"2026-07-05T04:47:20.956092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03066","created_at":"2026-07-05T04:47:20.956092+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVS73NEUOUKI","created_at":"2026-07-05T04:47:20.956092+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVS73NEUOUKID5L6","created_at":"2026-07-05T04:47:20.956092+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVS73NEU","created_at":"2026-07-05T04:47:20.956092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.19144","citing_title":"Prediction-Aware Learning in Multi-Agent Systems","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PVS73NEUOUKID5L6OJAGBTDEOC","json":"https://pith.science/pith/PVS73NEUOUKID5L6OJAGBTDEOC.json","graph_json":"https://pith.science/api/pith-number/PVS73NEUOUKID5L6OJAGBTDEOC/graph.json","events_json":"https://pith.science/api/pith-number/PVS73NEUOUKID5L6OJAGBTDEOC/events.json","paper":"https://pith.science/paper/PVS73NEU"},"agent_actions":{"view_html":"https://pith.science/pith/PVS73NEUOUKID5L6OJAGBTDEOC","download_json":"https://pith.science/pith/PVS73NEUOUKID5L6OJAGBTDEOC.json","view_paper":"https://pith.science/paper/PVS73NEU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.03066&json=true","fetch_graph":"https://pith.science/api/pith-number/PVS73NEUOUKID5L6OJAGBTDEOC/graph.json","fetch_events":"https://pith.science/api/pith-number/PVS73NEUOUKID5L6OJAGBTDEOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVS73NEUOUKID5L6OJAGBTDEOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVS73NEUOUKID5L6OJAGBTDEOC/action/storage_attestation","attest_author":"https://pith.science/pith/PVS73NEUOUKID5L6OJAGBTDEOC/action/author_attestation","sign_citation":"https://pith.science/pith/PVS73NEUOUKID5L6OJAGBTDEOC/action/citation_signature","submit_replication":"https://pith.science/pith/PVS73NEUOUKID5L6OJAGBTDEOC/action/replication_record"}},"created_at":"2026-07-05T04:47:20.956092+00:00","updated_at":"2026-07-05T04:47:20.956092+00:00"}