{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2001:VXPGMA4E4MC65PNRHN5FETLF4G","short_pith_number":"pith:VXPGMA4E","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"},"canonical_sha256":"adde660384e305eebdb13b7a524d65e18f1087a71f740974a5a4b2606b086809","source":{"kind":"arxiv","id":"cs/0105032","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/0105032","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"cs/0105032v1","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0105032","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"VXPGMA4E4MC6","created_at":"2026-05-18T12:25:50Z"},{"alias_kind":"pith_short_16","alias_value":"VXPGMA4E4MC65PNR","created_at":"2026-05-18T12:25:50Z"},{"alias_kind":"pith_short_8","alias_value":"VXPGMA4E","created_at":"2026-05-18T12:25:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2001:VXPGMA4E4MC65PNRHN5FETLF4G","target":"record","payload":{"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"},"canonical_sha256":"adde660384e305eebdb13b7a524d65e18f1087a71f740974a5a4b2606b086809","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"},"source_kind":"arxiv","source_id":"cs/0105032","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rCbNoApXzrl1ZPNTe0wiVNdXmkfgEX0K6OtevLoTTATbCx5t0WPS3t4vJ34qcwy0uoabvhMv34/hWkT74WR7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T03:18:27.973035Z"},"content_sha256":"ecb6d799d62068fbd7aac1499c93be67f5b1aa076db8a488492377cf5bcef8ed","schema_version":"1.0","event_id":"sha256:ecb6d799d62068fbd7aac1499c93be67f5b1aa076db8a488492377cf5bcef8ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2001:VXPGMA4E4MC65PNRHN5FETLF4G","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nXNieeiJBFo4mqHRfi92jWDubo/rkrzkchhYL3uGL7XZikhmEuRYfGS/eMJlQJQKRKHqCS5bngbRBAdlz4lFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T03:18:27.973691Z"},"content_sha256":"f0abd12728b90aa3f332a581b5dcd04c6481fda0323ac223daff5b15b8fd0b2c","schema_version":"1.0","event_id":"sha256:f0abd12728b90aa3f332a581b5dcd04c6481fda0323ac223daff5b15b8fd0b2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G/bundle.json","state_url":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VXPGMA4E4MC65PNRHN5FETLF4G/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T03:18:27Z","links":{"resolver":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G","bundle":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G/bundle.json","state":"https://pith.science/pith/VXPGMA4E4MC65PNRHN5FETLF4G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VXPGMA4E4MC65PNRHN5FETLF4G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2001:VXPGMA4E4MC65PNRHN5FETLF4G","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":["cs.MA"],"license":"","primary_cat":"cs.LG","submitted_at":"2001-05-25T02:52:07Z","title_canon_sha256":"a4ed5bb21308c18b0d52909461fa180efafcc28ba668c1f584da3c3221028c85"},"schema_version":"1.0","source":{"id":"cs/0105032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"cs/0105032","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"cs/0105032v1","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0105032","created_at":"2026-05-18T00:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"VXPGMA4E4MC6","created_at":"2026-05-18T12:25:50Z"},{"alias_kind":"pith_short_16","alias_value":"VXPGMA4E4MC65PNR","created_at":"2026-05-18T12:25:50Z"},{"alias_kind":"pith_short_8","alias_value":"VXPGMA4E","created_at":"2026-05-18T12:25:50Z"}],"graph_snapshots":[{"event_id":"sha256:f0abd12728b90aa3f332a581b5dcd04c6481fda0323ac223daff5b15b8fd0b2c","target":"graph","created_at":"2026-05-18T00:43:44Z","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":["cs.MA"],"headline":"","license":"","primary_cat":"cs.LG","submitted_at":"2001-05-25T02:52:07Z","title":"Learning to Cooperate via Policy Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0105032","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:ecb6d799d62068fbd7aac1499c93be67f5b1aa076db8a488492377cf5bcef8ed","target":"record","created_at":"2026-05-18T00:43:44Z","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":["cs.MA"],"license":"","primary_cat":"cs.LG","submitted_at":"2001-05-25T02:52:07Z","title_canon_sha256":"a4ed5bb21308c18b0d52909461fa180efafcc28ba668c1f584da3c3221028c85"},"schema_version":"1.0","source":{"id":"cs/0105032","kind":"arxiv","version":1}},"canonical_sha256":"adde660384e305eebdb13b7a524d65e18f1087a71f740974a5a4b2606b086809","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adde660384e305eebdb13b7a524d65e18f1087a71f740974a5a4b2606b086809","first_computed_at":"2026-05-18T00:43:44.000014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:44.000014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WWaXvYE1VGn2RPUMkKkqkY0RSBBoh8tGIANy1AX7uI+mOwdlMtomy01QRcpT6uaeKz3W3qIDjMCuzpoSrQqQCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:44.000578Z","signed_message":"canonical_sha256_bytes"},"source_id":"cs/0105032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecb6d799d62068fbd7aac1499c93be67f5b1aa076db8a488492377cf5bcef8ed","sha256:f0abd12728b90aa3f332a581b5dcd04c6481fda0323ac223daff5b15b8fd0b2c"],"state_sha256":"63b0df9e8ed5019e24374fc3c99aafffbdc8f549d1e08160bf950a69cfa48800"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U/PscM8rwXOPjm4pGhz5uYRrYnlmrNmgrZ5Kfbdh+Xx5TSDNZKj+DrfyNiwo0s3BPlo8nxtPU18WJhtGjT41Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T03:18:27.976994Z","bundle_sha256":"87fec388390aca6f6cedcd03bba90bad203c9c1befa912c7c6819faa5f72d0cf"}}