{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YJP56GMOZIXOE2QZEQNYPRTMEH","short_pith_number":"pith:YJP56GMO","schema_version":"1.0","canonical_sha256":"c25fdf198eca2ee26a19241b87c66c21fcab38cfd2c63fe0bbb8891b65dac8b7","source":{"kind":"arxiv","id":"2401.03896","version":1},"attestation_state":"computed","paper":{"title":"A Tensor Network Implementation of Multi Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Sunny Howard","submitted_at":"2024-01-08T13:50:49Z","abstract_excerpt":"Recently it has been shown that tensor networks (TNs) have the ability to represent the expected return of a single-agent finite Markov decision process (FMDP). The TN represents a distribution model, where all possible trajectories are considered. When extending these ideas to a multi-agent setting, distribution models suffer from the curse of dimensionality: the exponential relation between the number of possible trajectories and the number of agents. The key advantage of using TNs in this setting is that there exists a large number of established optimisation and decomposition techniques th"},"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":"2401.03896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-08T13:50:49Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"b3fde8ed110fcb2c256fe4b5aa53b402afefb377fe075ce6c6d6f9254f8c223f","abstract_canon_sha256":"e945aa18cccec9d9ec17ef9ea6cbfad4b35bd558aa59303b7474fe9a1d3f5a97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:31:14.998650Z","signature_b64":"3DIjgqc91QZDjZiYHHA8OoLj6N+NKVI90tQd7Fl13bG8tG8tnmYwNXcDwEPDlhrd2in137jwhpk8ZALzkvgnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c25fdf198eca2ee26a19241b87c66c21fcab38cfd2c63fe0bbb8891b65dac8b7","last_reissued_at":"2026-07-05T07:31:14.998262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:31:14.998262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Tensor Network Implementation of Multi Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Sunny Howard","submitted_at":"2024-01-08T13:50:49Z","abstract_excerpt":"Recently it has been shown that tensor networks (TNs) have the ability to represent the expected return of a single-agent finite Markov decision process (FMDP). The TN represents a distribution model, where all possible trajectories are considered. When extending these ideas to a multi-agent setting, distribution models suffer from the curse of dimensionality: the exponential relation between the number of possible trajectories and the number of agents. The key advantage of using TNs in this setting is that there exists a large number of established optimisation and decomposition techniques th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03896","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.03896/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2401.03896","created_at":"2026-07-05T07:31:14.998327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03896v1","created_at":"2026-07-05T07:31:14.998327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03896","created_at":"2026-07-05T07:31:14.998327+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJP56GMOZIXO","created_at":"2026-07-05T07:31:14.998327+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJP56GMOZIXOE2QZ","created_at":"2026-07-05T07:31:14.998327+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJP56GMO","created_at":"2026-07-05T07:31:14.998327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJP56GMOZIXOE2QZEQNYPRTMEH","json":"https://pith.science/pith/YJP56GMOZIXOE2QZEQNYPRTMEH.json","graph_json":"https://pith.science/api/pith-number/YJP56GMOZIXOE2QZEQNYPRTMEH/graph.json","events_json":"https://pith.science/api/pith-number/YJP56GMOZIXOE2QZEQNYPRTMEH/events.json","paper":"https://pith.science/paper/YJP56GMO"},"agent_actions":{"view_html":"https://pith.science/pith/YJP56GMOZIXOE2QZEQNYPRTMEH","download_json":"https://pith.science/pith/YJP56GMOZIXOE2QZEQNYPRTMEH.json","view_paper":"https://pith.science/paper/YJP56GMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03896&json=true","fetch_graph":"https://pith.science/api/pith-number/YJP56GMOZIXOE2QZEQNYPRTMEH/graph.json","fetch_events":"https://pith.science/api/pith-number/YJP56GMOZIXOE2QZEQNYPRTMEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJP56GMOZIXOE2QZEQNYPRTMEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJP56GMOZIXOE2QZEQNYPRTMEH/action/storage_attestation","attest_author":"https://pith.science/pith/YJP56GMOZIXOE2QZEQNYPRTMEH/action/author_attestation","sign_citation":"https://pith.science/pith/YJP56GMOZIXOE2QZEQNYPRTMEH/action/citation_signature","submit_replication":"https://pith.science/pith/YJP56GMOZIXOE2QZEQNYPRTMEH/action/replication_record"}},"created_at":"2026-07-05T07:31:14.998327+00:00","updated_at":"2026-07-05T07:31:14.998327+00:00"}