{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SGLARGUX73PK3NP72OUJDRDYAM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c830aec143671596f1deaf4f3c5cae678bfdf0bc1352bcebf10c72473daf77eb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T17:01:38Z","title_canon_sha256":"1a959a61e04e22d410d482107f7cbbc6fcf8239ec6a87e69beced929b368c3ba"},"schema_version":"1.0","source":{"id":"2404.10728","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10728","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10728v2","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10728","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"pith_short_12","alias_value":"SGLARGUX73PK","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"pith_short_16","alias_value":"SGLARGUX73PK3NP7","created_at":"2026-07-05T10:22:45Z"},{"alias_kind":"pith_short_8","alias_value":"SGLARGUX","created_at":"2026-07-05T10:22:45Z"}],"graph_snapshots":[{"event_id":"sha256:a90b485cb9a0ee411445dc661ba86fcfc65a3efec68b22a9732902dabf0ed504","target":"graph","created_at":"2026-07-05T10:22:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.10728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hao-Lun Hsu, Miroslav Pajic, Pan Xu, Weixin Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T17:01:38Z","title":"Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10728","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8908cf13f861ba516c56e45412c4507cd52f6885db988ae0908e128e3899844b","target":"record","created_at":"2026-07-05T10:22:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c830aec143671596f1deaf4f3c5cae678bfdf0bc1352bcebf10c72473daf77eb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-16T17:01:38Z","title_canon_sha256":"1a959a61e04e22d410d482107f7cbbc6fcf8239ec6a87e69beced929b368c3ba"},"schema_version":"1.0","source":{"id":"2404.10728","kind":"arxiv","version":2}},"canonical_sha256":"9196089a97fedeadb5ffd3a891c478030938bdf05d8b91a56d2cf1b0d085f1fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9196089a97fedeadb5ffd3a891c478030938bdf05d8b91a56d2cf1b0d085f1fa","first_computed_at":"2026-07-05T10:22:45.357287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:45.357287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U2rDIRXHFh1glXu7f0O4foB+FYGC6NsXiaB7x8jvhqpDFhtNAhm2EHBKJl40Fxh8OFx9Lb58Rym41req6VjjBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:45.357897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10728","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8908cf13f861ba516c56e45412c4507cd52f6885db988ae0908e128e3899844b","sha256:a90b485cb9a0ee411445dc661ba86fcfc65a3efec68b22a9732902dabf0ed504"],"state_sha256":"c499e4dc79e0c4dbaa7f64a2ee62f247dc87a1761270b3b21baf206b633db343"}