{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SWG23O5X3HMI6KNBMX6K6RZ5UN","short_pith_number":"pith:SWG23O5X","schema_version":"1.0","canonical_sha256":"958dadbbb7d9d88f29a165fcaf473da37b4a56ffd07cebaf477fac610e13bf73","source":{"kind":"arxiv","id":"2110.07392","version":2},"attestation_state":"computed","paper":{"title":"Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","math.OC"],"primary_cat":"cs.LG","authors_text":"Justin Lidard, Naomi Ehrich Leonard, Udari Madhushani","submitted_at":"2021-10-14T14:27:27Z","abstract_excerpt":"A challenge in reinforcement learning (RL) is minimizing the cost of sampling associated with exploration. Distributed exploration reduces sampling complexity in multi-agent RL (MARL). We investigate the benefits to performance in MARL when exploration is fully decentralized. Specifically, we consider a class of online, episodic, tabular $Q$-learning problems under time-varying reward and transition dynamics, in which agents can communicate in a decentralized manner.We show that group performance, as measured by the bound on regret, can be significantly improved through communication when each"},"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":"2110.07392","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-14T14:27:27Z","cross_cats_sorted":["cs.MA","math.OC"],"title_canon_sha256":"1f1b9dde08f3ea8e09264fd609468c1b728692bbc705b7a99e82e9ebd6056cb9","abstract_canon_sha256":"9b74ec37688ba044b738f8eda4982636659c4446638459e299a757abd00dd026"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:22.598531Z","signature_b64":"aulzAds3chyoxKARzv2czjkyVI4Ql9pdm1O1xb7IjoCcj6K5tmL4GuKdInRBgLYb7xw5cLc4wNwGnCY0uHEmCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"958dadbbb7d9d88f29a165fcaf473da37b4a56ffd07cebaf477fac610e13bf73","last_reissued_at":"2026-07-05T04:19:22.598065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:22.598065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Efficient Multi-Agent Reinforcement Learning with Fully Decentralized Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","math.OC"],"primary_cat":"cs.LG","authors_text":"Justin Lidard, Naomi Ehrich Leonard, Udari Madhushani","submitted_at":"2021-10-14T14:27:27Z","abstract_excerpt":"A challenge in reinforcement learning (RL) is minimizing the cost of sampling associated with exploration. Distributed exploration reduces sampling complexity in multi-agent RL (MARL). We investigate the benefits to performance in MARL when exploration is fully decentralized. Specifically, we consider a class of online, episodic, tabular $Q$-learning problems under time-varying reward and transition dynamics, in which agents can communicate in a decentralized manner.We show that group performance, as measured by the bound on regret, can be significantly improved through communication when each"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07392","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/2110.07392/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":"2110.07392","created_at":"2026-07-05T04:19:22.598126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.07392v2","created_at":"2026-07-05T04:19:22.598126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07392","created_at":"2026-07-05T04:19:22.598126+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWG23O5X3HMI","created_at":"2026-07-05T04:19:22.598126+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWG23O5X3HMI6KNB","created_at":"2026-07-05T04:19:22.598126+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWG23O5X","created_at":"2026-07-05T04:19:22.598126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN","json":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN.json","graph_json":"https://pith.science/api/pith-number/SWG23O5X3HMI6KNBMX6K6RZ5UN/graph.json","events_json":"https://pith.science/api/pith-number/SWG23O5X3HMI6KNBMX6K6RZ5UN/events.json","paper":"https://pith.science/paper/SWG23O5X"},"agent_actions":{"view_html":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN","download_json":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN.json","view_paper":"https://pith.science/paper/SWG23O5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.07392&json=true","fetch_graph":"https://pith.science/api/pith-number/SWG23O5X3HMI6KNBMX6K6RZ5UN/graph.json","fetch_events":"https://pith.science/api/pith-number/SWG23O5X3HMI6KNBMX6K6RZ5UN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN/action/storage_attestation","attest_author":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN/action/author_attestation","sign_citation":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN/action/citation_signature","submit_replication":"https://pith.science/pith/SWG23O5X3HMI6KNBMX6K6RZ5UN/action/replication_record"}},"created_at":"2026-07-05T04:19:22.598126+00:00","updated_at":"2026-07-05T04:19:22.598126+00:00"}