{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OSUN35YHUB76VX7UHSOO2FCWAE","short_pith_number":"pith:OSUN35YH","schema_version":"1.0","canonical_sha256":"74a8ddf707a07feadff43c9ced14560128d7314135316aa03a9987b17e8c76f6","source":{"kind":"arxiv","id":"2405.06161","version":5},"attestation_state":"computed","paper":{"title":"An Initial Introduction to Cooperative Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Christopher Amato","submitted_at":"2024-05-10T00:50:08Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) has exploded in popularity in recent years. While numerous approaches have been developed, they can be broadly categorized into three main types: centralized training and execution (CTE), centralized training for decentralized execution (CTDE), and decentralized training and execution (DTE). CTE methods assume centralization during training and execution (e.g., with fast, free, and perfect communication) and have the most information during execution. CTDE methods are the most common, as they leverage centralized information during training while enabl"},"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":"2405.06161","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-10T00:50:08Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"435f9d3bcb020d5f523e5561a60708f3818934d98e8058640e1aa8900fa043d5","abstract_canon_sha256":"b16a85411bfa8e1a7d428a3ec6f94781c6841a037813510dad03d60c7b1be3e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:20.834162Z","signature_b64":"FxA7/ojDPXOIXQ7AjxKvBJz+vb+cUYNJexnenxP01CPutBbX+BelZT/1qMEvGtfEooD+RYtGMgnsatcxKdP+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74a8ddf707a07feadff43c9ced14560128d7314135316aa03a9987b17e8c76f6","last_reissued_at":"2026-07-05T11:06:20.833621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:20.833621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Initial Introduction to Cooperative Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Christopher Amato","submitted_at":"2024-05-10T00:50:08Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) has exploded in popularity in recent years. While numerous approaches have been developed, they can be broadly categorized into three main types: centralized training and execution (CTE), centralized training for decentralized execution (CTDE), and decentralized training and execution (DTE). CTE methods assume centralization during training and execution (e.g., with fast, free, and perfect communication) and have the most information during execution. CTDE methods are the most common, as they leverage centralized information during training while enabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06161","kind":"arxiv","version":5},"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/2405.06161/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":"2405.06161","created_at":"2026-07-05T11:06:20.833691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.06161v5","created_at":"2026-07-05T11:06:20.833691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06161","created_at":"2026-07-05T11:06:20.833691+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSUN35YHUB76","created_at":"2026-07-05T11:06:20.833691+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSUN35YHUB76VX7U","created_at":"2026-07-05T11:06:20.833691+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSUN35YH","created_at":"2026-07-05T11:06:20.833691+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22982","citing_title":"Distilling Collaborative Dynamics into Latent Space for Implicit Coordination in Decentralized Multi-Agent Manipulation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22982","citing_title":"Distilling Collaborative Dynamics into Latent Space for Implicit Coordination in Decentralized Multi-Agent Manipulation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OSUN35YHUB76VX7UHSOO2FCWAE","json":"https://pith.science/pith/OSUN35YHUB76VX7UHSOO2FCWAE.json","graph_json":"https://pith.science/api/pith-number/OSUN35YHUB76VX7UHSOO2FCWAE/graph.json","events_json":"https://pith.science/api/pith-number/OSUN35YHUB76VX7UHSOO2FCWAE/events.json","paper":"https://pith.science/paper/OSUN35YH"},"agent_actions":{"view_html":"https://pith.science/pith/OSUN35YHUB76VX7UHSOO2FCWAE","download_json":"https://pith.science/pith/OSUN35YHUB76VX7UHSOO2FCWAE.json","view_paper":"https://pith.science/paper/OSUN35YH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.06161&json=true","fetch_graph":"https://pith.science/api/pith-number/OSUN35YHUB76VX7UHSOO2FCWAE/graph.json","fetch_events":"https://pith.science/api/pith-number/OSUN35YHUB76VX7UHSOO2FCWAE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSUN35YHUB76VX7UHSOO2FCWAE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSUN35YHUB76VX7UHSOO2FCWAE/action/storage_attestation","attest_author":"https://pith.science/pith/OSUN35YHUB76VX7UHSOO2FCWAE/action/author_attestation","sign_citation":"https://pith.science/pith/OSUN35YHUB76VX7UHSOO2FCWAE/action/citation_signature","submit_replication":"https://pith.science/pith/OSUN35YHUB76VX7UHSOO2FCWAE/action/replication_record"}},"created_at":"2026-07-05T11:06:20.833691+00:00","updated_at":"2026-07-05T11:06:20.833691+00:00"}