{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YX522BHEFTNUCVKNHRHOW4WCUQ","short_pith_number":"pith:YX522BHE","schema_version":"1.0","canonical_sha256":"c5fbad04e42cdb41554d3c4eeb72c2a41a2d8fa331ac1d81be760427708e6da2","source":{"kind":"arxiv","id":"2309.14792","version":4},"attestation_state":"computed","paper":{"title":"Exploiting Local Observations for Robust Robot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Eetu-Aleksi Rantala, Joni Pajarinen, Jorge Pe\\~na Queralta, Sahar Salimpour, Wenshuai Zhao, Zhiyuan Li","submitted_at":"2023-09-26T09:40:35Z","abstract_excerpt":"While many robotic tasks can be addressed using either centralized single-agent control with full state observation or decentralized multi-agent control, clear criteria for choosing between these approaches remain underexplored. This paper systematically investigates how multi-agent reinforcement learning (MARL) with local observations can improve robustness in complex robotic systems compared to traditional centralized control. Through theoretical analysis and empirical validation, we show that in certain tasks, decentralized MARL can achieve performance comparable to centralized methods whil"},"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":"2309.14792","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-09-26T09:40:35Z","cross_cats_sorted":[],"title_canon_sha256":"f28a196585a7cbdf94c31d084fc059c8381aa7b44ded6d0a381b57d12031b07d","abstract_canon_sha256":"0db954cfd8f1138b0b0b20dfc5d6faa1f61e2e667ece72d9e26427a1d7b31685"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:52.071701Z","signature_b64":"Tu2vgm3TuwtPndntVP25b1ihXe2y2+1nNISwuUxgEpaNA0p5XO1O8bRudnB004HpUTxHXMn21o5VGM3y/7owCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5fbad04e42cdb41554d3c4eeb72c2a41a2d8fa331ac1d81be760427708e6da2","last_reissued_at":"2026-07-05T11:45:52.071148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:52.071148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Local Observations for Robust Robot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Eetu-Aleksi Rantala, Joni Pajarinen, Jorge Pe\\~na Queralta, Sahar Salimpour, Wenshuai Zhao, Zhiyuan Li","submitted_at":"2023-09-26T09:40:35Z","abstract_excerpt":"While many robotic tasks can be addressed using either centralized single-agent control with full state observation or decentralized multi-agent control, clear criteria for choosing between these approaches remain underexplored. This paper systematically investigates how multi-agent reinforcement learning (MARL) with local observations can improve robustness in complex robotic systems compared to traditional centralized control. Through theoretical analysis and empirical validation, we show that in certain tasks, decentralized MARL can achieve performance comparable to centralized methods whil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14792","kind":"arxiv","version":4},"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/2309.14792/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":"2309.14792","created_at":"2026-07-05T11:45:52.071221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.14792v4","created_at":"2026-07-05T11:45:52.071221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14792","created_at":"2026-07-05T11:45:52.071221+00:00"},{"alias_kind":"pith_short_12","alias_value":"YX522BHEFTNU","created_at":"2026-07-05T11:45:52.071221+00:00"},{"alias_kind":"pith_short_16","alias_value":"YX522BHEFTNUCVKN","created_at":"2026-07-05T11:45:52.071221+00:00"},{"alias_kind":"pith_short_8","alias_value":"YX522BHE","created_at":"2026-07-05T11:45:52.071221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.13846","citing_title":"Causal Knowledge Transfer for Multi-Agent Reinforcement Learning in Dynamic Environments","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YX522BHEFTNUCVKNHRHOW4WCUQ","json":"https://pith.science/pith/YX522BHEFTNUCVKNHRHOW4WCUQ.json","graph_json":"https://pith.science/api/pith-number/YX522BHEFTNUCVKNHRHOW4WCUQ/graph.json","events_json":"https://pith.science/api/pith-number/YX522BHEFTNUCVKNHRHOW4WCUQ/events.json","paper":"https://pith.science/paper/YX522BHE"},"agent_actions":{"view_html":"https://pith.science/pith/YX522BHEFTNUCVKNHRHOW4WCUQ","download_json":"https://pith.science/pith/YX522BHEFTNUCVKNHRHOW4WCUQ.json","view_paper":"https://pith.science/paper/YX522BHE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.14792&json=true","fetch_graph":"https://pith.science/api/pith-number/YX522BHEFTNUCVKNHRHOW4WCUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YX522BHEFTNUCVKNHRHOW4WCUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YX522BHEFTNUCVKNHRHOW4WCUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YX522BHEFTNUCVKNHRHOW4WCUQ/action/storage_attestation","attest_author":"https://pith.science/pith/YX522BHEFTNUCVKNHRHOW4WCUQ/action/author_attestation","sign_citation":"https://pith.science/pith/YX522BHEFTNUCVKNHRHOW4WCUQ/action/citation_signature","submit_replication":"https://pith.science/pith/YX522BHEFTNUCVKNHRHOW4WCUQ/action/replication_record"}},"created_at":"2026-07-05T11:45:52.071221+00:00","updated_at":"2026-07-05T11:45:52.071221+00:00"}