{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D5VL5PJYTTJKKQNXWIAVCOVU5X","short_pith_number":"pith:D5VL5PJY","schema_version":"1.0","canonical_sha256":"1f6abebd389cd2a541b7b201513ab4edc90f86186d3791099e8e3a89c137a5ca","source":{"kind":"arxiv","id":"2310.14685","version":2},"attestation_state":"computed","paper":{"title":"Multi-Agent Learning in Contextual Games under Unknown Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.GT","authors_text":"Anna M. Maddux, Maryam Kamgarpour","submitted_at":"2023-10-23T08:25:14Z","abstract_excerpt":"We consider the problem of learning to play a repeated contextual game with unknown reward and unknown constraints functions. Such games arise in applications where each agent's action needs to belong to a feasible set, but the feasible set is a priori unknown. For example, in constrained multi-agent reinforcement learning, the constraints on the agents' policies are a function of the unknown dynamics and hence, are themselves unknown. Under kernel-based regularity assumptions on the unknown functions, we develop a no-regret, no-violation approach which exploits similarities among different re"},"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":"2310.14685","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GT","submitted_at":"2023-10-23T08:25:14Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"05af4d87ca9056f300cdc96a06eb00f6c43a875125fcdf0760292eebde3a5ce2","abstract_canon_sha256":"56ecb8f3cde841bfbcc0e31e2dabdf6c558ab4bd8aa65ad4f13a7636179425d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:34.348809Z","signature_b64":"/NIN/bHiZxCsnUi405D0iH538XQc/8uZnbnu4UcXpvPmfVD/v1RiguyaS6iWoDqykB8stFaisi30ut2aaa4ECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f6abebd389cd2a541b7b201513ab4edc90f86186d3791099e8e3a89c137a5ca","last_reissued_at":"2026-07-05T08:22:34.348285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:34.348285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Learning in Contextual Games under Unknown Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.GT","authors_text":"Anna M. Maddux, Maryam Kamgarpour","submitted_at":"2023-10-23T08:25:14Z","abstract_excerpt":"We consider the problem of learning to play a repeated contextual game with unknown reward and unknown constraints functions. Such games arise in applications where each agent's action needs to belong to a feasible set, but the feasible set is a priori unknown. For example, in constrained multi-agent reinforcement learning, the constraints on the agents' policies are a function of the unknown dynamics and hence, are themselves unknown. Under kernel-based regularity assumptions on the unknown functions, we develop a no-regret, no-violation approach which exploits similarities among different re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14685","kind":"arxiv","version":2},"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/2310.14685/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":"2310.14685","created_at":"2026-07-05T08:22:34.348360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14685v2","created_at":"2026-07-05T08:22:34.348360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14685","created_at":"2026-07-05T08:22:34.348360+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5VL5PJYTTJK","created_at":"2026-07-05T08:22:34.348360+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5VL5PJYTTJKKQNX","created_at":"2026-07-05T08:22:34.348360+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5VL5PJY","created_at":"2026-07-05T08:22:34.348360+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":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5VL5PJYTTJKKQNXWIAVCOVU5X","json":"https://pith.science/pith/D5VL5PJYTTJKKQNXWIAVCOVU5X.json","graph_json":"https://pith.science/api/pith-number/D5VL5PJYTTJKKQNXWIAVCOVU5X/graph.json","events_json":"https://pith.science/api/pith-number/D5VL5PJYTTJKKQNXWIAVCOVU5X/events.json","paper":"https://pith.science/paper/D5VL5PJY"},"agent_actions":{"view_html":"https://pith.science/pith/D5VL5PJYTTJKKQNXWIAVCOVU5X","download_json":"https://pith.science/pith/D5VL5PJYTTJKKQNXWIAVCOVU5X.json","view_paper":"https://pith.science/paper/D5VL5PJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14685&json=true","fetch_graph":"https://pith.science/api/pith-number/D5VL5PJYTTJKKQNXWIAVCOVU5X/graph.json","fetch_events":"https://pith.science/api/pith-number/D5VL5PJYTTJKKQNXWIAVCOVU5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5VL5PJYTTJKKQNXWIAVCOVU5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5VL5PJYTTJKKQNXWIAVCOVU5X/action/storage_attestation","attest_author":"https://pith.science/pith/D5VL5PJYTTJKKQNXWIAVCOVU5X/action/author_attestation","sign_citation":"https://pith.science/pith/D5VL5PJYTTJKKQNXWIAVCOVU5X/action/citation_signature","submit_replication":"https://pith.science/pith/D5VL5PJYTTJKKQNXWIAVCOVU5X/action/replication_record"}},"created_at":"2026-07-05T08:22:34.348360+00:00","updated_at":"2026-07-05T08:22:34.348360+00:00"}