{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EVOJOTMRDPSINMLPOCWAPXNCFM","short_pith_number":"pith:EVOJOTMR","schema_version":"1.0","canonical_sha256":"255c974d911be486b16f70ac07dda22b1cfe23592331adcb341dd77b74bbf2cd","source":{"kind":"arxiv","id":"2301.03398","version":2},"attestation_state":"computed","paper":{"title":"Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chao Yu, Huazhong Yang, Jiaxuan Gao, Jiayu Chen, Jijia Liu, Ruixin Huang, Xinyi Yang, Yi Wu, Yunfei Li, Yunfei Xiang, Yu Wang","submitted_at":"2023-01-09T14:53:38Z","abstract_excerpt":"We consider the problem of cooperative exploration where multiple robots need to cooperatively explore an unknown region as fast as possible. Multi-agent reinforcement learning (MARL) has recently become a trending paradigm for solving this challenge. However, existing MARL-based methods adopt action-making steps as the metric for exploration efficiency by assuming all the agents are acting in a fully synchronous manner: i.e., every single agent produces an action simultaneously and every single action is executed instantaneously at each time step. Despite its mathematical simplicity, such a s"},"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":"2301.03398","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-01-09T14:53:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3294b7aaed3f479c9bc863a97613c06461071e3d3717f7f8231e623c38f48163","abstract_canon_sha256":"61ae1574b7a761d84375d5f30794d3ec3eccf6653ba375a323e497d421acc0e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:43.938179Z","signature_b64":"iuzt2lsrg0lQWrcsrYswa2enC0VTd2rfcHalUpw1jog5dBfHQfgcdvew6p83un9USF9weRG/BzlfqkzLVT8WBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"255c974d911be486b16f70ac07dda22b1cfe23592331adcb341dd77b74bbf2cd","last_reissued_at":"2026-07-05T05:59:43.937759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:43.937759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chao Yu, Huazhong Yang, Jiaxuan Gao, Jiayu Chen, Jijia Liu, Ruixin Huang, Xinyi Yang, Yi Wu, Yunfei Li, Yunfei Xiang, Yu Wang","submitted_at":"2023-01-09T14:53:38Z","abstract_excerpt":"We consider the problem of cooperative exploration where multiple robots need to cooperatively explore an unknown region as fast as possible. Multi-agent reinforcement learning (MARL) has recently become a trending paradigm for solving this challenge. However, existing MARL-based methods adopt action-making steps as the metric for exploration efficiency by assuming all the agents are acting in a fully synchronous manner: i.e., every single agent produces an action simultaneously and every single action is executed instantaneously at each time step. Despite its mathematical simplicity, such a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.03398","kind":"arxiv","version":2},"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/2301.03398/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":"2301.03398","created_at":"2026-07-05T05:59:43.937816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.03398v2","created_at":"2026-07-05T05:59:43.937816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.03398","created_at":"2026-07-05T05:59:43.937816+00:00"},{"alias_kind":"pith_short_12","alias_value":"EVOJOTMRDPSI","created_at":"2026-07-05T05:59:43.937816+00:00"},{"alias_kind":"pith_short_16","alias_value":"EVOJOTMRDPSINMLP","created_at":"2026-07-05T05:59:43.937816+00:00"},{"alias_kind":"pith_short_8","alias_value":"EVOJOTMR","created_at":"2026-07-05T05:59:43.937816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2502.00558","citing_title":"Asynchronous Cooperative Multi-Agent Reinforcement Learning with Limited Communication","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EVOJOTMRDPSINMLPOCWAPXNCFM","json":"https://pith.science/pith/EVOJOTMRDPSINMLPOCWAPXNCFM.json","graph_json":"https://pith.science/api/pith-number/EVOJOTMRDPSINMLPOCWAPXNCFM/graph.json","events_json":"https://pith.science/api/pith-number/EVOJOTMRDPSINMLPOCWAPXNCFM/events.json","paper":"https://pith.science/paper/EVOJOTMR"},"agent_actions":{"view_html":"https://pith.science/pith/EVOJOTMRDPSINMLPOCWAPXNCFM","download_json":"https://pith.science/pith/EVOJOTMRDPSINMLPOCWAPXNCFM.json","view_paper":"https://pith.science/paper/EVOJOTMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.03398&json=true","fetch_graph":"https://pith.science/api/pith-number/EVOJOTMRDPSINMLPOCWAPXNCFM/graph.json","fetch_events":"https://pith.science/api/pith-number/EVOJOTMRDPSINMLPOCWAPXNCFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EVOJOTMRDPSINMLPOCWAPXNCFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EVOJOTMRDPSINMLPOCWAPXNCFM/action/storage_attestation","attest_author":"https://pith.science/pith/EVOJOTMRDPSINMLPOCWAPXNCFM/action/author_attestation","sign_citation":"https://pith.science/pith/EVOJOTMRDPSINMLPOCWAPXNCFM/action/citation_signature","submit_replication":"https://pith.science/pith/EVOJOTMRDPSINMLPOCWAPXNCFM/action/replication_record"}},"created_at":"2026-07-05T05:59:43.937816+00:00","updated_at":"2026-07-05T05:59:43.937816+00:00"}