{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5JGNABN55UVSHC2GQHT2W4CB2O","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":"8e2601f1d043d95374a2deca574bc566403ebaed64baf9ffca8a2415cc91f165","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-06T20:58:58Z","title_canon_sha256":"0f843f9d765494cc1099e8a0d2c927263c250379edde7e791f3f3f0d593c5366"},"schema_version":"1.0","source":{"id":"2002.02513","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.02513","created_at":"2026-07-05T04:33:17Z"},{"alias_kind":"arxiv_version","alias_value":"2002.02513v7","created_at":"2026-07-05T04:33:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02513","created_at":"2026-07-05T04:33:17Z"},{"alias_kind":"pith_short_12","alias_value":"5JGNABN55UVS","created_at":"2026-07-05T04:33:17Z"},{"alias_kind":"pith_short_16","alias_value":"5JGNABN55UVSHC2G","created_at":"2026-07-05T04:33:17Z"},{"alias_kind":"pith_short_8","alias_value":"5JGNABN5","created_at":"2026-07-05T04:33:17Z"}],"graph_snapshots":[{"event_id":"sha256:1518e5b460fe979c682c72a916e78bf99f07e0b4aa61d5e63b37e528137fbbfa","target":"graph","created_at":"2026-07-05T04:33:17Z","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/2002.02513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mean field theory provides an effective way of scaling multiagent reinforcement learning algorithms to environments with many agents that can be abstracted by a virtual mean agent. In this paper, we extend mean field multiagent algorithms to multiple types. The types enable the relaxation of a core assumption in mean field reinforcement learning, which is that all agents in the environment are playing almost similar strategies and have the same goal. We conduct experiments on three different testbeds for the field of many agent reinforcement learning, based on the standard MAgents framework. W","authors_text":"Matthew E. Taylor, Nidhi Hegde, Pascal Poupart, Sriram Ganapathi Subramanian","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-06T20:58:58Z","title":"Multi Type Mean Field Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02513","kind":"arxiv","version":7},"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:dc881dc39aaea6a62de301224c40114354fb82004a9f254993536c87cb3d408d","target":"record","created_at":"2026-07-05T04:33:17Z","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":"8e2601f1d043d95374a2deca574bc566403ebaed64baf9ffca8a2415cc91f165","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2020-02-06T20:58:58Z","title_canon_sha256":"0f843f9d765494cc1099e8a0d2c927263c250379edde7e791f3f3f0d593c5366"},"schema_version":"1.0","source":{"id":"2002.02513","kind":"arxiv","version":7}},"canonical_sha256":"ea4cd005bded2b238b4681e7ab7041d3b78dc59da0d60e984d5d8fb77090c507","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea4cd005bded2b238b4681e7ab7041d3b78dc59da0d60e984d5d8fb77090c507","first_computed_at":"2026-07-05T04:33:17.355813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:17.355813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mQECTzKwXuMnreqwjW7B6mLRfwcBZsdy5Fnlq+71RQnarwdHAJf6SyhosOgkyseQR2QWRfAveR0AkYvvfratCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:17.358951Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.02513","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc881dc39aaea6a62de301224c40114354fb82004a9f254993536c87cb3d408d","sha256:1518e5b460fe979c682c72a916e78bf99f07e0b4aa61d5e63b37e528137fbbfa"],"state_sha256":"b388a150982b6ca940c30da976755c64aa8358d906fc63a5dbaed955e190170e"}