{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4NRC2BQW7TVOBAKZ6YWLZDB44A","short_pith_number":"pith:4NRC2BQW","schema_version":"1.0","canonical_sha256":"e3622d0616fceae08159f62cbc8c3ce036d84b92556111bdb6d4e719037fe786","source":{"kind":"arxiv","id":"2602.12386","version":2},"attestation_state":"computed","paper":{"title":"Provably Convergent Actor-Critic for MARL through Risk-aversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"cs.MA","authors_text":"Eric Mazumdar, Yizhou Zhang","submitted_at":"2026-02-12T20:29:41Z","abstract_excerpt":"Learning stationary policies in infinite-horizon general-sum Markov games (MGs) remains a fundamental open problem in Multi-Agent Reinforcement Learning (MARL). While stationary strategies are preferred for their practicality, computing stationary forms of classic game-theoretic equilibria is computationally intractable -- a stark contrast to the comparative ease of solving single-agent RL or zero-sum games. To bridge this gap, we study Risk-averse Quantal response Equilibria (RQE), a solution concept rooted in behavioral game theory that incorporates risk aversion and bounded rationality. We "},"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":"2602.12386","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-02-12T20:29:41Z","cross_cats_sorted":["cs.GT","cs.LG"],"title_canon_sha256":"e5c8bf9912340e1a5d4fa45aca0e75d9d3178f5e7a48feeb11f63388966f719c","abstract_canon_sha256":"c8dcaaab48ca3462e01e62809e3d819244305626ba4b39bf9f6ba353a6f25123"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:34.169074Z","signature_b64":"taV1kPnQK61zGix3zhfzFELcrL9I+rLIwRbUGLGTHGnSLgDjSv28BMmNlFX3K8pnCHMP1uKn4wLXu/MjexsrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3622d0616fceae08159f62cbc8c3ce036d84b92556111bdb6d4e719037fe786","last_reissued_at":"2026-06-01T01:02:34.168077Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:34.168077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Convergent Actor-Critic for MARL through Risk-aversion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT","cs.LG"],"primary_cat":"cs.MA","authors_text":"Eric Mazumdar, Yizhou Zhang","submitted_at":"2026-02-12T20:29:41Z","abstract_excerpt":"Learning stationary policies in infinite-horizon general-sum Markov games (MGs) remains a fundamental open problem in Multi-Agent Reinforcement Learning (MARL). While stationary strategies are preferred for their practicality, computing stationary forms of classic game-theoretic equilibria is computationally intractable -- a stark contrast to the comparative ease of solving single-agent RL or zero-sum games. To bridge this gap, we study Risk-averse Quantal response Equilibria (RQE), a solution concept rooted in behavioral game theory that incorporates risk aversion and bounded rationality. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12386","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/2602.12386/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":"2602.12386","created_at":"2026-06-01T01:02:34.168197+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.12386v2","created_at":"2026-06-01T01:02:34.168197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12386","created_at":"2026-06-01T01:02:34.168197+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NRC2BQW7TVO","created_at":"2026-06-01T01:02:34.168197+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NRC2BQW7TVOBAKZ","created_at":"2026-06-01T01:02:34.168197+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NRC2BQW","created_at":"2026-06-01T01:02:34.168197+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.22318","citing_title":"Strategically Robust Linear Quadratic Dynamic Games","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A","json":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A.json","graph_json":"https://pith.science/api/pith-number/4NRC2BQW7TVOBAKZ6YWLZDB44A/graph.json","events_json":"https://pith.science/api/pith-number/4NRC2BQW7TVOBAKZ6YWLZDB44A/events.json","paper":"https://pith.science/paper/4NRC2BQW"},"agent_actions":{"view_html":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A","download_json":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A.json","view_paper":"https://pith.science/paper/4NRC2BQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.12386&json=true","fetch_graph":"https://pith.science/api/pith-number/4NRC2BQW7TVOBAKZ6YWLZDB44A/graph.json","fetch_events":"https://pith.science/api/pith-number/4NRC2BQW7TVOBAKZ6YWLZDB44A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A/action/storage_attestation","attest_author":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A/action/author_attestation","sign_citation":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A/action/citation_signature","submit_replication":"https://pith.science/pith/4NRC2BQW7TVOBAKZ6YWLZDB44A/action/replication_record"}},"created_at":"2026-06-01T01:02:34.168197+00:00","updated_at":"2026-06-01T01:02:34.168197+00:00"}