{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2001:VXPGMA4E4MC65PNRHN5FETLF4G","short_pith_number":"pith:VXPGMA4E","schema_version":"1.0","canonical_sha256":"adde660384e305eebdb13b7a524d65e18f1087a71f740974a5a4b2606b086809","source":{"kind":"arxiv","id":"cs/0105032","version":1},"attestation_state":"computed","paper":{"title":"Learning to Cooperate via Policy Search","license":"","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Kee-Eung Kim, Leonid Peshkin, Leslie Pack Kaelbling, Nicolas Meuleau","submitted_at":"2001-05-25T02:52:07Z","abstract_excerpt":"Cooperative games are those in which both agents share the same payoff structure. Value-based reinforcement-learning algorithms, such as variants of Q-learning, have been applied to learning cooperative games, but they only apply when the game state is completely observable to both agents. Policy search methods are a reasonable alternative to value-based methods for partially observable environments. In this paper, we provide a gradient-based distributed policy-search method for cooperative games and compare the notion of local optimum to that of Nash equilibrium. We demonstrate the effectiven"},"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":"cs/0105032","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.LG","submitted_at":"2001-05-25T02:52:07Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"a4ed5bb21308c18b0d52909461fa180efafcc28ba668c1f584da3c3221028c85","abstract_canon_sha256":"2ef12c6a60669c2adbd49311c5d1153dd1d4e16f75df1974ecef922c5e0838c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:44.000578Z","signature_b64":"WWaXvYE1VGn2RPUMkKkqkY0RSBBoh8tGIANy1AX7uI+mOwdlMtomy01QRcpT6uaeKz3W3qIDjMCuzpoSrQqQCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adde660384e305eebdb13b7a524d65e18f1087a71f740974a5a4b2606b086809","last_reissued_at":"2026-05-18T00:43:44.000014Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:44.000014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Cooperate via Policy Search","license":"","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Kee-Eung Kim, Leonid Peshkin, Leslie Pack Kaelbling, Nicolas Meuleau","submitted_at":"2001-05-25T02:52:07Z","abstract_excerpt":"Cooperative games are those in which both agents share the same payoff structure. Value-based reinforcement-learning algorithms, such as variants of Q-learning, have been applied to learning cooperative games, but they only apply when the game state is completely observable to both agents. Policy search methods are a reasonable alternative to value-based methods for partially observable environments. In this paper, we provide a gradient-based distributed policy-search method for cooperative games and compare the notion of local optimum to that of Nash equilibrium. We demonstrate the effectiven"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0105032","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":""},"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":"cs/0105032","created_at":"2026-05-18T00:43:44.000090+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0105032v1","created_at":"2026-05-18T00:43:44.000090+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0105032","created_at":"2026-05-18T00:43:44.000090+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXPGMA4E4MC6","created_at":"2026-05-18T12:25:50.845339+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXPGMA4E4MC65PNR","created_at":"2026-05-18T12:25:50.845339+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXPGMA4E","created_at":"2026-05-18T12:25:50.845339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2601.21972","citing_title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06595","citing_title":"Cross-Modal Navigation with Multi-Agent Reinforcement Learning","ref_index":69,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G","json":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G.json","graph_json":"https://pith.science/api/pith-number/VXPGMA4E4MC65PNRHN5FETLF4G/graph.json","events_json":"https://pith.science/api/pith-number/VXPGMA4E4MC65PNRHN5FETLF4G/events.json","paper":"https://pith.science/paper/VXPGMA4E"},"agent_actions":{"view_html":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G","download_json":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G.json","view_paper":"https://pith.science/paper/VXPGMA4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0105032&json=true","fetch_graph":"https://pith.science/api/pith-number/VXPGMA4E4MC65PNRHN5FETLF4G/graph.json","fetch_events":"https://pith.science/api/pith-number/VXPGMA4E4MC65PNRHN5FETLF4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G/action/storage_attestation","attest_author":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G/action/author_attestation","sign_citation":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G/action/citation_signature","submit_replication":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G/action/replication_record"}},"created_at":"2026-05-18T00:43:44.000090+00:00","updated_at":"2026-05-18T00:43:44.000090+00:00"}