{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Y45UKSPPZEH7HK3AKCSJDB2BDB","short_pith_number":"pith:Y45UKSPP","schema_version":"1.0","canonical_sha256":"c73b4549efc90ff3ab6050a4918741185698cd5dee21308f38807e290da7fdd4","source":{"kind":"arxiv","id":"2211.02127","version":3},"attestation_state":"computed","paper":{"title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.MA","authors_text":"Hamsa Balakrishnan, Karthik Gopalakrishnan, Kenneth Choi, Siddharth Nayak, Sydney Dolan, Wenqi Ding","submitted_at":"2022-11-03T20:02:45Z","abstract_excerpt":"We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent. We propose InforMARL, a novel architecture for multi-agent reinforcement learning (MARL) which uses local information intelligently to compute paths for all the agents in a decentralized manner. Specifically, InforMARL aggregates information about the local neighborhood of agents for both the actor and the critic using a graph neural network and can be used in conjunction with any standard MARL algorithm. We show that (1) in training, InforMARL has be"},"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":"2211.02127","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-11-03T20:02:45Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"6d1294ddcc1054a5f8c817e47209391ac6a1d12d43b11c194b524c6c867e773b","abstract_canon_sha256":"2ccd3403bc9dd03fb6ff65a4a215ca8c120234918d3f753a86cc65cb74e5a6a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:21.575893Z","signature_b64":"JJane33ukEuzm1PCQmKR+B1gxKBF0WLM+Qg0NWdOa0GxVukJBr7BUHE4cfy+rW5/XLYwTt4slPs/RjSNG7nkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c73b4549efc90ff3ab6050a4918741185698cd5dee21308f38807e290da7fdd4","last_reissued_at":"2026-07-05T06:10:21.575388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:21.575388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.MA","authors_text":"Hamsa Balakrishnan, Karthik Gopalakrishnan, Kenneth Choi, Siddharth Nayak, Sydney Dolan, Wenqi Ding","submitted_at":"2022-11-03T20:02:45Z","abstract_excerpt":"We consider the problem of multi-agent navigation and collision avoidance when observations are limited to the local neighborhood of each agent. We propose InforMARL, a novel architecture for multi-agent reinforcement learning (MARL) which uses local information intelligently to compute paths for all the agents in a decentralized manner. Specifically, InforMARL aggregates information about the local neighborhood of agents for both the actor and the critic using a graph neural network and can be used in conjunction with any standard MARL algorithm. We show that (1) in training, InforMARL has be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02127","kind":"arxiv","version":3},"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/2211.02127/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":"2211.02127","created_at":"2026-07-05T06:10:21.575458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.02127v3","created_at":"2026-07-05T06:10:21.575458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02127","created_at":"2026-07-05T06:10:21.575458+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y45UKSPPZEH7","created_at":"2026-07-05T06:10:21.575458+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y45UKSPPZEH7HK3A","created_at":"2026-07-05T06:10:21.575458+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y45UKSPP","created_at":"2026-07-05T06:10:21.575458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13200","citing_title":"SRMT: Shared Memory for Multi-agent Lifelong Pathfinding","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y45UKSPPZEH7HK3AKCSJDB2BDB","json":"https://pith.science/pith/Y45UKSPPZEH7HK3AKCSJDB2BDB.json","graph_json":"https://pith.science/api/pith-number/Y45UKSPPZEH7HK3AKCSJDB2BDB/graph.json","events_json":"https://pith.science/api/pith-number/Y45UKSPPZEH7HK3AKCSJDB2BDB/events.json","paper":"https://pith.science/paper/Y45UKSPP"},"agent_actions":{"view_html":"https://pith.science/pith/Y45UKSPPZEH7HK3AKCSJDB2BDB","download_json":"https://pith.science/pith/Y45UKSPPZEH7HK3AKCSJDB2BDB.json","view_paper":"https://pith.science/paper/Y45UKSPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.02127&json=true","fetch_graph":"https://pith.science/api/pith-number/Y45UKSPPZEH7HK3AKCSJDB2BDB/graph.json","fetch_events":"https://pith.science/api/pith-number/Y45UKSPPZEH7HK3AKCSJDB2BDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y45UKSPPZEH7HK3AKCSJDB2BDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y45UKSPPZEH7HK3AKCSJDB2BDB/action/storage_attestation","attest_author":"https://pith.science/pith/Y45UKSPPZEH7HK3AKCSJDB2BDB/action/author_attestation","sign_citation":"https://pith.science/pith/Y45UKSPPZEH7HK3AKCSJDB2BDB/action/citation_signature","submit_replication":"https://pith.science/pith/Y45UKSPPZEH7HK3AKCSJDB2BDB/action/replication_record"}},"created_at":"2026-07-05T06:10:21.575458+00:00","updated_at":"2026-07-05T06:10:21.575458+00:00"}