{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JLOBCTOR3CFF6KP4NGKZBRYUNV","short_pith_number":"pith:JLOBCTOR","schema_version":"1.0","canonical_sha256":"4adc114dd1d88a5f29fc699590c7146d7db46ab27eacebde3a9f217ee76e8a5f","source":{"kind":"arxiv","id":"2303.14061","version":4},"attestation_state":"computed","paper":{"title":"Learning Reward Machines in Cooperative Multi-Agent Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MA","cs.SC"],"primary_cat":"cs.AI","authors_text":"Alessandra Russo, Daniel Furelos-Blanco, Leo Ardon","submitted_at":"2023-03-24T15:12:28Z","abstract_excerpt":"This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks. The proposed method helps deal with the non-Markovian nature of the rewards in partially observable environments and improves the interpretability of the learnt policies required to complete the cooperative task. The RMs associated with each sub-task are learnt in a decentralised manner and then used to guide the behaviour of each agent. By doing so, the complexity of a cooperative mult"},"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":"2303.14061","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-24T15:12:28Z","cross_cats_sorted":["cs.MA","cs.SC"],"title_canon_sha256":"d6bff939802bd3cb6ccfb03ee0a3dfe6c7f4497771a9fbdd37ed54bb8046442c","abstract_canon_sha256":"3f0f2b9cdbe40ea2c4f5efafbbbd0aed68bfcb1a4317df9e4908e0458e5e0331"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:01.250232Z","signature_b64":"xxDh/OgXrTTY0W8h4CqkXOHnTFtlywzTBl7SenlCzaulfDL9KkCA9jHQ54a3lc0hAuCKWV1bVdl5arVWfcXdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4adc114dd1d88a5f29fc699590c7146d7db46ab27eacebde3a9f217ee76e8a5f","last_reissued_at":"2026-07-05T10:14:01.249759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:01.249759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Reward Machines in Cooperative Multi-Agent Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MA","cs.SC"],"primary_cat":"cs.AI","authors_text":"Alessandra Russo, Daniel Furelos-Blanco, Leo Ardon","submitted_at":"2023-03-24T15:12:28Z","abstract_excerpt":"This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks. The proposed method helps deal with the non-Markovian nature of the rewards in partially observable environments and improves the interpretability of the learnt policies required to complete the cooperative task. The RMs associated with each sub-task are learnt in a decentralised manner and then used to guide the behaviour of each agent. By doing so, the complexity of a cooperative mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14061","kind":"arxiv","version":4},"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/2303.14061/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":"2303.14061","created_at":"2026-07-05T10:14:01.249819+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14061v4","created_at":"2026-07-05T10:14:01.249819+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14061","created_at":"2026-07-05T10:14:01.249819+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLOBCTOR3CFF","created_at":"2026-07-05T10:14:01.249819+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLOBCTOR3CFF6KP4","created_at":"2026-07-05T10:14:01.249819+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLOBCTOR","created_at":"2026-07-05T10:14:01.249819+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/JLOBCTOR3CFF6KP4NGKZBRYUNV","json":"https://pith.science/pith/JLOBCTOR3CFF6KP4NGKZBRYUNV.json","graph_json":"https://pith.science/api/pith-number/JLOBCTOR3CFF6KP4NGKZBRYUNV/graph.json","events_json":"https://pith.science/api/pith-number/JLOBCTOR3CFF6KP4NGKZBRYUNV/events.json","paper":"https://pith.science/paper/JLOBCTOR"},"agent_actions":{"view_html":"https://pith.science/pith/JLOBCTOR3CFF6KP4NGKZBRYUNV","download_json":"https://pith.science/pith/JLOBCTOR3CFF6KP4NGKZBRYUNV.json","view_paper":"https://pith.science/paper/JLOBCTOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14061&json=true","fetch_graph":"https://pith.science/api/pith-number/JLOBCTOR3CFF6KP4NGKZBRYUNV/graph.json","fetch_events":"https://pith.science/api/pith-number/JLOBCTOR3CFF6KP4NGKZBRYUNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLOBCTOR3CFF6KP4NGKZBRYUNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLOBCTOR3CFF6KP4NGKZBRYUNV/action/storage_attestation","attest_author":"https://pith.science/pith/JLOBCTOR3CFF6KP4NGKZBRYUNV/action/author_attestation","sign_citation":"https://pith.science/pith/JLOBCTOR3CFF6KP4NGKZBRYUNV/action/citation_signature","submit_replication":"https://pith.science/pith/JLOBCTOR3CFF6KP4NGKZBRYUNV/action/replication_record"}},"created_at":"2026-07-05T10:14:01.249819+00:00","updated_at":"2026-07-05T10:14:01.249819+00:00"}