{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SGLARGUX73PK3NP72OUJDRDYAM","short_pith_number":"pith:SGLARGUX","schema_version":"1.0","canonical_sha256":"9196089a97fedeadb5ffd3a891c478030938bdf05d8b91a56d2cf1b0d085f1fa","source":{"kind":"arxiv","id":"2404.10728","version":2},"attestation_state":"computed","paper":{"title":"Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao-Lun Hsu, Miroslav Pajic, Pan Xu, Weixin Wang","submitted_at":"2024-04-16T17:01:38Z","abstract_excerpt":"We present the first study on provably efficient randomized exploration in cooperative multi-agent reinforcement learning (MARL). We propose a unified algorithm framework for randomized exploration in parallel Markov Decision Processes (MDPs), and two Thompson Sampling (TS)-type algorithms, CoopTS-PHE and CoopTS-LMC, incorporating the perturbed-history exploration (PHE) strategy and the Langevin Monte Carlo exploration (LMC) strategy, respectively, which are flexible in design and easy to implement in practice. For a special class of parallel MDPs where the transition is (approximately) linear"},"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":"2404.10728","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T17:01:38Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1a959a61e04e22d410d482107f7cbbc6fcf8239ec6a87e69beced929b368c3ba","abstract_canon_sha256":"c830aec143671596f1deaf4f3c5cae678bfdf0bc1352bcebf10c72473daf77eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:45.357897Z","signature_b64":"U2rDIRXHFh1glXu7f0O4foB+FYGC6NsXiaB7x8jvhqpDFhtNAhm2EHBKJl40Fxh8OFx9Lb58Rym41req6VjjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9196089a97fedeadb5ffd3a891c478030938bdf05d8b91a56d2cf1b0d085f1fa","last_reissued_at":"2026-07-05T10:22:45.357287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:45.357287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao-Lun Hsu, Miroslav Pajic, Pan Xu, Weixin Wang","submitted_at":"2024-04-16T17:01:38Z","abstract_excerpt":"We present the first study on provably efficient randomized exploration in cooperative multi-agent reinforcement learning (MARL). We propose a unified algorithm framework for randomized exploration in parallel Markov Decision Processes (MDPs), and two Thompson Sampling (TS)-type algorithms, CoopTS-PHE and CoopTS-LMC, incorporating the perturbed-history exploration (PHE) strategy and the Langevin Monte Carlo exploration (LMC) strategy, respectively, which are flexible in design and easy to implement in practice. For a special class of parallel MDPs where the transition is (approximately) linear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10728","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/2404.10728/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":"2404.10728","created_at":"2026-07-05T10:22:45.357367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10728v2","created_at":"2026-07-05T10:22:45.357367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10728","created_at":"2026-07-05T10:22:45.357367+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGLARGUX73PK","created_at":"2026-07-05T10:22:45.357367+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGLARGUX73PK3NP7","created_at":"2026-07-05T10:22:45.357367+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGLARGUX","created_at":"2026-07-05T10:22:45.357367+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24252","citing_title":"A Reward-driven Automated Webshell Malicious-code Generator for Red-teaming","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SGLARGUX73PK3NP72OUJDRDYAM","json":"https://pith.science/pith/SGLARGUX73PK3NP72OUJDRDYAM.json","graph_json":"https://pith.science/api/pith-number/SGLARGUX73PK3NP72OUJDRDYAM/graph.json","events_json":"https://pith.science/api/pith-number/SGLARGUX73PK3NP72OUJDRDYAM/events.json","paper":"https://pith.science/paper/SGLARGUX"},"agent_actions":{"view_html":"https://pith.science/pith/SGLARGUX73PK3NP72OUJDRDYAM","download_json":"https://pith.science/pith/SGLARGUX73PK3NP72OUJDRDYAM.json","view_paper":"https://pith.science/paper/SGLARGUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10728&json=true","fetch_graph":"https://pith.science/api/pith-number/SGLARGUX73PK3NP72OUJDRDYAM/graph.json","fetch_events":"https://pith.science/api/pith-number/SGLARGUX73PK3NP72OUJDRDYAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGLARGUX73PK3NP72OUJDRDYAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGLARGUX73PK3NP72OUJDRDYAM/action/storage_attestation","attest_author":"https://pith.science/pith/SGLARGUX73PK3NP72OUJDRDYAM/action/author_attestation","sign_citation":"https://pith.science/pith/SGLARGUX73PK3NP72OUJDRDYAM/action/citation_signature","submit_replication":"https://pith.science/pith/SGLARGUX73PK3NP72OUJDRDYAM/action/replication_record"}},"created_at":"2026-07-05T10:22:45.357367+00:00","updated_at":"2026-07-05T10:22:45.357367+00:00"}