{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QRWXMR3H65FLHBTYSRYYMEADVI","short_pith_number":"pith:QRWXMR3H","schema_version":"1.0","canonical_sha256":"846d764767f74ab386789471861003aa3d30e444d7680921a59845a5e53fb0a2","source":{"kind":"arxiv","id":"2307.16212","version":1},"attestation_state":"computed","paper":{"title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Fei Miao, Sanbao Su, Shaofeng Zou, Shuo Han, Sihong He, Songyang Han","submitted_at":"2023-07-30T12:31:42Z","abstract_excerpt":"In real-world multi-agent reinforcement learning (MARL) applications, agents may not have perfect state information (e.g., due to inaccurate measurement or malicious attacks), which challenges the robustness of agents' policies. Though robustness is getting important in MARL deployment, little prior work has studied state uncertainties in MARL, neither in problem formulation nor algorithm design. Motivated by this robustness issue and the lack of corresponding studies, we study the problem of MARL with state uncertainty in this work. We provide the first attempt to the theoretical and empirica"},"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":"2307.16212","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-30T12:31:42Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","cs.SY","eess.SY"],"title_canon_sha256":"fe6017c1a2224a57aed353b3557b0700db8f5e58e8344d3c0b615ef5ae468050","abstract_canon_sha256":"10c5f7bf736377b07a048a171be977586dc4dd71f94189231029e1547ba2a9e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:00.276181Z","signature_b64":"ertZA6keiHbxBmOKkzkL7SKRFv2E7o2BxLYGoTom18xyE6Tdmrn0ee3qUV24gnSAgx3aQYxzhQ3/OXZMkFDEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"846d764767f74ab386789471861003aa3d30e444d7680921a59845a5e53fb0a2","last_reissued_at":"2026-07-05T06:36:00.275731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:00.275731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Multi-Agent Reinforcement Learning with State Uncertainty","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Fei Miao, Sanbao Su, Shaofeng Zou, Shuo Han, Sihong He, Songyang Han","submitted_at":"2023-07-30T12:31:42Z","abstract_excerpt":"In real-world multi-agent reinforcement learning (MARL) applications, agents may not have perfect state information (e.g., due to inaccurate measurement or malicious attacks), which challenges the robustness of agents' policies. Though robustness is getting important in MARL deployment, little prior work has studied state uncertainties in MARL, neither in problem formulation nor algorithm design. Motivated by this robustness issue and the lack of corresponding studies, we study the problem of MARL with state uncertainty in this work. We provide the first attempt to the theoretical and empirica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16212","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/2307.16212/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":"2307.16212","created_at":"2026-07-05T06:36:00.275788+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16212v1","created_at":"2026-07-05T06:36:00.275788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16212","created_at":"2026-07-05T06:36:00.275788+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRWXMR3H65FL","created_at":"2026-07-05T06:36:00.275788+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRWXMR3H65FLHBTY","created_at":"2026-07-05T06:36:00.275788+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRWXMR3H","created_at":"2026-07-05T06:36:00.275788+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18024","citing_title":"Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02844","citing_title":"Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18024","citing_title":"Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01168","citing_title":"SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometry","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRWXMR3H65FLHBTYSRYYMEADVI","json":"https://pith.science/pith/QRWXMR3H65FLHBTYSRYYMEADVI.json","graph_json":"https://pith.science/api/pith-number/QRWXMR3H65FLHBTYSRYYMEADVI/graph.json","events_json":"https://pith.science/api/pith-number/QRWXMR3H65FLHBTYSRYYMEADVI/events.json","paper":"https://pith.science/paper/QRWXMR3H"},"agent_actions":{"view_html":"https://pith.science/pith/QRWXMR3H65FLHBTYSRYYMEADVI","download_json":"https://pith.science/pith/QRWXMR3H65FLHBTYSRYYMEADVI.json","view_paper":"https://pith.science/paper/QRWXMR3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16212&json=true","fetch_graph":"https://pith.science/api/pith-number/QRWXMR3H65FLHBTYSRYYMEADVI/graph.json","fetch_events":"https://pith.science/api/pith-number/QRWXMR3H65FLHBTYSRYYMEADVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRWXMR3H65FLHBTYSRYYMEADVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRWXMR3H65FLHBTYSRYYMEADVI/action/storage_attestation","attest_author":"https://pith.science/pith/QRWXMR3H65FLHBTYSRYYMEADVI/action/author_attestation","sign_citation":"https://pith.science/pith/QRWXMR3H65FLHBTYSRYYMEADVI/action/citation_signature","submit_replication":"https://pith.science/pith/QRWXMR3H65FLHBTYSRYYMEADVI/action/replication_record"}},"created_at":"2026-07-05T06:36:00.275788+00:00","updated_at":"2026-07-05T06:36:00.275788+00:00"}