{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:DG3IK3BE6GCDK7XTPIHN62OPYP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2ef12c6a60669c2adbd49311c5d1153dd1d4e16f75df1974ecef922c5e0838c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-08-07T06:25:37Z","title_canon_sha256":"a4ed5bb21308c18b0d52909461fa180efafcc28ba668c1f584da3c3221028c85"},"schema_version":"1.0","source":{"id":"1408.1484","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1408.1484","created_at":"2026-05-18T02:45:40Z"},{"alias_kind":"arxiv_version","alias_value":"1408.1484v1","created_at":"2026-05-18T02:45:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.1484","created_at":"2026-05-18T02:45:40Z"},{"alias_kind":"pith_short_12","alias_value":"DG3IK3BE6GCD","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_16","alias_value":"DG3IK3BE6GCDK7XT","created_at":"2026-05-18T12:28:25Z"},{"alias_kind":"pith_short_8","alias_value":"DG3IK3BE","created_at":"2026-05-18T12:28:25Z"}],"graph_snapshots":[{"event_id":"sha256:c1a2cf7c680b88880e9a65fff41174f58e16d0ab30cd0882defdf8926b175ce4","target":"graph","created_at":"2026-05-18T02:45:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Kee-Eung Kim, Leonid Peshkin, Leslie Pack Kaelbling, Nicolas Meuleau","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-08-07T06:25:37Z","title":"Learning to Cooperate via Policy Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.1484","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e243f7f7da65dd14737cc617389e0480013e37e38f37cfd3f14323d653b3976e","target":"record","created_at":"2026-05-18T02:45:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2ef12c6a60669c2adbd49311c5d1153dd1d4e16f75df1974ecef922c5e0838c0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2014-08-07T06:25:37Z","title_canon_sha256":"a4ed5bb21308c18b0d52909461fa180efafcc28ba668c1f584da3c3221028c85"},"schema_version":"1.0","source":{"id":"1408.1484","kind":"arxiv","version":1}},"canonical_sha256":"19b6856c24f184357ef37a0edf69cfc3f7d53ee4d1b06179c180aafcf25fe122","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19b6856c24f184357ef37a0edf69cfc3f7d53ee4d1b06179c180aafcf25fe122","first_computed_at":"2026-05-18T02:45:40.375039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:45:40.375039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nCMHvCg0zZXr00Iw3E3v5c6M1LRNrKMa+kVwv9mIhHUdv9i7uV2TyqyjrOuqyif63U8dTJx6bAxq1sTFM8qkDg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:45:40.375531Z","signed_message":"canonical_sha256_bytes"},"source_id":"1408.1484","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e243f7f7da65dd14737cc617389e0480013e37e38f37cfd3f14323d653b3976e","sha256:c1a2cf7c680b88880e9a65fff41174f58e16d0ab30cd0882defdf8926b175ce4"],"state_sha256":"f74f67bfe27194ed1ecce02e784c9a31a6f70647a628a7ecaf3102fbbc179b77"}