{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QCIPLNQ5ZYZOXL3PLSXE43YO3Y","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":"c6a0388c08955990855596ce32a0b89b87095ab9e7c10144f56c2aeae2470675","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-07-14T00:34:08Z","title_canon_sha256":"526e37b6a0b000c946a30097c6aa6b307e8fc5d4879809754352a6f08f4705c9"},"schema_version":"1.0","source":{"id":"2107.06434","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.06434","created_at":"2026-07-05T03:54:22Z"},{"alias_kind":"arxiv_version","alias_value":"2107.06434v2","created_at":"2026-07-05T03:54:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06434","created_at":"2026-07-05T03:54:22Z"},{"alias_kind":"pith_short_12","alias_value":"QCIPLNQ5ZYZO","created_at":"2026-07-05T03:54:22Z"},{"alias_kind":"pith_short_16","alias_value":"QCIPLNQ5ZYZOXL3P","created_at":"2026-07-05T03:54:22Z"},{"alias_kind":"pith_short_8","alias_value":"QCIPLNQ5","created_at":"2026-07-05T03:54:22Z"}],"graph_snapshots":[{"event_id":"sha256:741792c558774e678b735610e71ff212f24b141d2eb47fe3a654d26aa0c3f05f","target":"graph","created_at":"2026-07-05T03:54:22Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.06434/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) in partially observable, fully cooperative multi-agent settings (Dec-POMDPs) can in principle be used to address many real-world challenges such as controlling a swarm of rescue robots or a team of quadcopters. However, Dec-POMDPs are significantly harder to solve than single-agent problems, with the former being NEXP-complete and the latter, MDPs, being just P-complete. Hence, current RL algorithms for Dec-POMDPs suffer from poor sample complexity, which greatly reduces their applicability to practical problems where environment interaction is costly. Our key insig","authors_text":"Animesh Garg, Chris Lu, Jakob Foerster, Qizhen Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-07-14T00:34:08Z","title":"Centralized Model and Exploration Policy for Multi-Agent RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06434","kind":"arxiv","version":2},"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":"sha256:3fe559d74db9511cc1b508d6b75b715dd87fce7aea14321e50485d401dcdaec9","target":"record","created_at":"2026-07-05T03:54:22Z","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":"c6a0388c08955990855596ce32a0b89b87095ab9e7c10144f56c2aeae2470675","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-07-14T00:34:08Z","title_canon_sha256":"526e37b6a0b000c946a30097c6aa6b307e8fc5d4879809754352a6f08f4705c9"},"schema_version":"1.0","source":{"id":"2107.06434","kind":"arxiv","version":2}},"canonical_sha256":"8090f5b61dce32ebaf6f5cae4e6f0ede38efe88b63ed8c87aea596ab61cd5758","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8090f5b61dce32ebaf6f5cae4e6f0ede38efe88b63ed8c87aea596ab61cd5758","first_computed_at":"2026-07-05T03:54:22.048019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:54:22.048019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JezOvZllu6vUF0QCeKg+8bVg5XcHWK+p9NeGD7kPzspgG/Ss8mtaapF8LBVd8GMb0zl/CrdLAXwak1GPLCq9AA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:54:22.048479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.06434","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fe559d74db9511cc1b508d6b75b715dd87fce7aea14321e50485d401dcdaec9","sha256:741792c558774e678b735610e71ff212f24b141d2eb47fe3a654d26aa0c3f05f"],"state_sha256":"ef9e742f4267d11e214191319cdae6cbb0227561c78987190088cf33b7e0ff79"}