{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SJC6ZTW7KGLPM227Q457FSZTGO","short_pith_number":"pith:SJC6ZTW7","schema_version":"1.0","canonical_sha256":"9245eccedf5196f66b5f873bf2cb33338a475e27da57b8e46a0b66a0168ffbf9","source":{"kind":"arxiv","id":"2507.23604","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrea Cini, Cesare Alippi, Tommaso Marzi","submitted_at":"2025-07-31T14:42:12Z","abstract_excerpt":"Decentralized Multi-Agent Reinforcement Learning (MARL) methods allow for learning scalable multi-agent policies, but suffer from partial observability and induced non-stationarity. These challenges can be addressed by introducing mechanisms that facilitate coordination and high-level planning. Specifically, coordination and temporal abstraction can be achieved through communication (e.g., message passing) and Hierarchical Reinforcement Learning (HRL) approaches to decision-making. However, optimization issues limit the applicability of hierarchical policies to multi-agent systems. As such, th"},"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":"2507.23604","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-31T14:42:12Z","cross_cats_sorted":[],"title_canon_sha256":"e28bf4bc90cca9d826a740a8b26e8e5d40926a5caad3980f50077a10d3c8c9c2","abstract_canon_sha256":"9e2c7b1ccd794a8ba7384b0054a6462369c530a58369fc911b936ed594b2fef8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:40.672663Z","signature_b64":"8fN6HXIk/5owBduyVOI+Tm8pw81aRTwQR/xvNnaBnvr9y4mQCWkgXW962JsRVSRhLN5EYU97MSMz4Q7CtkPBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9245eccedf5196f66b5f873bf2cb33338a475e27da57b8e46a0b66a0168ffbf9","last_reissued_at":"2026-07-01T01:17:40.672061Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:40.672061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andrea Cini, Cesare Alippi, Tommaso Marzi","submitted_at":"2025-07-31T14:42:12Z","abstract_excerpt":"Decentralized Multi-Agent Reinforcement Learning (MARL) methods allow for learning scalable multi-agent policies, but suffer from partial observability and induced non-stationarity. These challenges can be addressed by introducing mechanisms that facilitate coordination and high-level planning. Specifically, coordination and temporal abstraction can be achieved through communication (e.g., message passing) and Hierarchical Reinforcement Learning (HRL) approaches to decision-making. However, optimization issues limit the applicability of hierarchical policies to multi-agent systems. As such, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23604","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/2507.23604/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":"2507.23604","created_at":"2026-07-01T01:17:40.672132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23604v2","created_at":"2026-07-01T01:17:40.672132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23604","created_at":"2026-07-01T01:17:40.672132+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJC6ZTW7KGLP","created_at":"2026-07-01T01:17:40.672132+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJC6ZTW7KGLPM227","created_at":"2026-07-01T01:17:40.672132+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJC6ZTW7","created_at":"2026-07-01T01:17:40.672132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.29126","citing_title":"HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO","json":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO.json","graph_json":"https://pith.science/api/pith-number/SJC6ZTW7KGLPM227Q457FSZTGO/graph.json","events_json":"https://pith.science/api/pith-number/SJC6ZTW7KGLPM227Q457FSZTGO/events.json","paper":"https://pith.science/paper/SJC6ZTW7"},"agent_actions":{"view_html":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO","download_json":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO.json","view_paper":"https://pith.science/paper/SJC6ZTW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23604&json=true","fetch_graph":"https://pith.science/api/pith-number/SJC6ZTW7KGLPM227Q457FSZTGO/graph.json","fetch_events":"https://pith.science/api/pith-number/SJC6ZTW7KGLPM227Q457FSZTGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO/action/storage_attestation","attest_author":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO/action/author_attestation","sign_citation":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO/action/citation_signature","submit_replication":"https://pith.science/pith/SJC6ZTW7KGLPM227Q457FSZTGO/action/replication_record"}},"created_at":"2026-07-01T01:17:40.672132+00:00","updated_at":"2026-07-01T01:17:40.672132+00:00"}