{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:EA4452G37UDPIO3RNQLJFXKFJC","short_pith_number":"pith:EA4452G3","schema_version":"1.0","canonical_sha256":"2039cee8dbfd06f43b716c1692dd4548acfcd1e1d064d521227e24ac13b7bc98","source":{"kind":"arxiv","id":"2105.07405","version":2},"attestation_state":"computed","paper":{"title":"Robust optimal policies for team Markov games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Feng Huang, Long Wang, Ming Cao","submitted_at":"2021-05-16T10:42:09Z","abstract_excerpt":"In stochastic dynamic environments, team Markov games have emerged as a versatile paradigm for studying sequential decision-making problems of fully cooperative multi-agent systems. However, the optimality of the derived policies is usually sensitive to model parameters, which are typically unknown and required to be estimated from noisy data in practice. To mitigate the sensitivity of optimal policies to these uncertain parameters, we propose a robust model of team Markov games in this paper, where agents utilize robust optimization approaches to update strategies. This model extends team Mar"},"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":"2105.07405","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2021-05-16T10:42:09Z","cross_cats_sorted":["cs.AI","cs.GT","cs.MA","cs.SY","eess.SY"],"title_canon_sha256":"82a9daae0b6f5cdd1e64d04f03eea048aa7e98389f7cfcc7ca5387c95b4f0547","abstract_canon_sha256":"54a8b866f63fc343235752f89006a757eeb7a0c6e44b14f6c5baf2680e2e7ee8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:02.080450Z","signature_b64":"SB+J6Se8GnGi8USy6E7SDronXiS9x8mesdYe7pfTVJcLoUplxG9pkFbG+uA7PBMF1bCvcKS1cotKTw0MReyNBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2039cee8dbfd06f43b716c1692dd4548acfcd1e1d064d521227e24ac13b7bc98","last_reissued_at":"2026-07-05T04:19:02.079843Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:02.079843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust optimal policies for team Markov games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","cs.MA","cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Feng Huang, Long Wang, Ming Cao","submitted_at":"2021-05-16T10:42:09Z","abstract_excerpt":"In stochastic dynamic environments, team Markov games have emerged as a versatile paradigm for studying sequential decision-making problems of fully cooperative multi-agent systems. However, the optimality of the derived policies is usually sensitive to model parameters, which are typically unknown and required to be estimated from noisy data in practice. To mitigate the sensitivity of optimal policies to these uncertain parameters, we propose a robust model of team Markov games in this paper, where agents utilize robust optimization approaches to update strategies. This model extends team Mar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.07405","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/2105.07405/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":"2105.07405","created_at":"2026-07-05T04:19:02.079909+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.07405v2","created_at":"2026-07-05T04:19:02.079909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.07405","created_at":"2026-07-05T04:19:02.079909+00:00"},{"alias_kind":"pith_short_12","alias_value":"EA4452G37UDP","created_at":"2026-07-05T04:19:02.079909+00:00"},{"alias_kind":"pith_short_16","alias_value":"EA4452G37UDPIO3R","created_at":"2026-07-05T04:19:02.079909+00:00"},{"alias_kind":"pith_short_8","alias_value":"EA4452G3","created_at":"2026-07-05T04:19:02.079909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EA4452G37UDPIO3RNQLJFXKFJC","json":"https://pith.science/pith/EA4452G37UDPIO3RNQLJFXKFJC.json","graph_json":"https://pith.science/api/pith-number/EA4452G37UDPIO3RNQLJFXKFJC/graph.json","events_json":"https://pith.science/api/pith-number/EA4452G37UDPIO3RNQLJFXKFJC/events.json","paper":"https://pith.science/paper/EA4452G3"},"agent_actions":{"view_html":"https://pith.science/pith/EA4452G37UDPIO3RNQLJFXKFJC","download_json":"https://pith.science/pith/EA4452G37UDPIO3RNQLJFXKFJC.json","view_paper":"https://pith.science/paper/EA4452G3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.07405&json=true","fetch_graph":"https://pith.science/api/pith-number/EA4452G37UDPIO3RNQLJFXKFJC/graph.json","fetch_events":"https://pith.science/api/pith-number/EA4452G37UDPIO3RNQLJFXKFJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EA4452G37UDPIO3RNQLJFXKFJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EA4452G37UDPIO3RNQLJFXKFJC/action/storage_attestation","attest_author":"https://pith.science/pith/EA4452G37UDPIO3RNQLJFXKFJC/action/author_attestation","sign_citation":"https://pith.science/pith/EA4452G37UDPIO3RNQLJFXKFJC/action/citation_signature","submit_replication":"https://pith.science/pith/EA4452G37UDPIO3RNQLJFXKFJC/action/replication_record"}},"created_at":"2026-07-05T04:19:02.079909+00:00","updated_at":"2026-07-05T04:19:02.079909+00:00"}