{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CEQ5VLIUKUUFI4ONHIPYUHE4KQ","short_pith_number":"pith:CEQ5VLIU","schema_version":"1.0","canonical_sha256":"1121daad1455285471cd3a1f8a1c9c5438d05f5d3b7bf911f497e89d6e1033cb","source":{"kind":"arxiv","id":"2504.20593","version":1},"attestation_state":"computed","paper":{"title":"Independent Learning in Performative Markov Potential Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Debmalya Mandal, Goran Radanovi\\'c, Paulius Sasnauskas, Rilind Sahitaj, Yi\\u{g}it Yal{\\i}n","submitted_at":"2025-04-29T09:46:16Z","abstract_excerpt":"Performative Reinforcement Learning (PRL) refers to a scenario in which the deployed policy changes the reward and transition dynamics of the underlying environment. In this work, we study multi-agent PRL by incorporating performative effects into Markov Potential Games (MPGs). We introduce the notion of a performatively stable equilibrium (PSE) and show that it always exists under a reasonable sensitivity assumption. We then provide convergence results for state-of-the-art algorithms used to solve MPGs. Specifically, we show that independent policy gradient ascent (IPGA) and independent natur"},"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":"2504.20593","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T09:46:16Z","cross_cats_sorted":[],"title_canon_sha256":"5dd334f2bab02a58b89cdd1e40c2ddf37217fa2f47c34fffd1a129ff373baf17","abstract_canon_sha256":"444cc94a790fd8a749baa28f1fbb3f2ad82067d11a4ec6cb1a6ea3296ce8806e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:45.251163Z","signature_b64":"f78eWYbYRtyrhyfPH/UxfWFwTLY9ACzpy2hqKk1QCf2yG9nHEbEMeCq2ST7GuRqp4fQMqNytnAWAgmsjBuNqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1121daad1455285471cd3a1f8a1c9c5438d05f5d3b7bf911f497e89d6e1033cb","last_reissued_at":"2026-07-05T10:55:45.250657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:45.250657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Independent Learning in Performative Markov Potential Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Debmalya Mandal, Goran Radanovi\\'c, Paulius Sasnauskas, Rilind Sahitaj, Yi\\u{g}it Yal{\\i}n","submitted_at":"2025-04-29T09:46:16Z","abstract_excerpt":"Performative Reinforcement Learning (PRL) refers to a scenario in which the deployed policy changes the reward and transition dynamics of the underlying environment. In this work, we study multi-agent PRL by incorporating performative effects into Markov Potential Games (MPGs). We introduce the notion of a performatively stable equilibrium (PSE) and show that it always exists under a reasonable sensitivity assumption. We then provide convergence results for state-of-the-art algorithms used to solve MPGs. Specifically, we show that independent policy gradient ascent (IPGA) and independent natur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20593","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/2504.20593/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":"2504.20593","created_at":"2026-07-05T10:55:45.250724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20593v1","created_at":"2026-07-05T10:55:45.250724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20593","created_at":"2026-07-05T10:55:45.250724+00:00"},{"alias_kind":"pith_short_12","alias_value":"CEQ5VLIUKUUF","created_at":"2026-07-05T10:55:45.250724+00:00"},{"alias_kind":"pith_short_16","alias_value":"CEQ5VLIUKUUFI4ON","created_at":"2026-07-05T10:55:45.250724+00:00"},{"alias_kind":"pith_short_8","alias_value":"CEQ5VLIU","created_at":"2026-07-05T10:55:45.250724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07101","citing_title":"Decentralized Diffusion Policy Learning for Enhanced Exploration in Cooperative Multi-agent Reinforcement Learning","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ","json":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ.json","graph_json":"https://pith.science/api/pith-number/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/graph.json","events_json":"https://pith.science/api/pith-number/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/events.json","paper":"https://pith.science/paper/CEQ5VLIU"},"agent_actions":{"view_html":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ","download_json":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ.json","view_paper":"https://pith.science/paper/CEQ5VLIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20593&json=true","fetch_graph":"https://pith.science/api/pith-number/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/action/storage_attestation","attest_author":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/action/author_attestation","sign_citation":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/action/citation_signature","submit_replication":"https://pith.science/pith/CEQ5VLIUKUUFI4ONHIPYUHE4KQ/action/replication_record"}},"created_at":"2026-07-05T10:55:45.250724+00:00","updated_at":"2026-07-05T10:55:45.250724+00:00"}