{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:JLOBCTOR3CFF6KP4NGKZBRYUNV","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":"3f0f2b9cdbe40ea2c4f5efafbbbd0aed68bfcb1a4317df9e4908e0458e5e0331","cross_cats_sorted":["cs.MA","cs.SC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-24T15:12:28Z","title_canon_sha256":"d6bff939802bd3cb6ccfb03ee0a3dfe6c7f4497771a9fbdd37ed54bb8046442c"},"schema_version":"1.0","source":{"id":"2303.14061","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14061","created_at":"2026-07-05T10:14:01Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14061v4","created_at":"2026-07-05T10:14:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14061","created_at":"2026-07-05T10:14:01Z"},{"alias_kind":"pith_short_12","alias_value":"JLOBCTOR3CFF","created_at":"2026-07-05T10:14:01Z"},{"alias_kind":"pith_short_16","alias_value":"JLOBCTOR3CFF6KP4","created_at":"2026-07-05T10:14:01Z"},{"alias_kind":"pith_short_8","alias_value":"JLOBCTOR","created_at":"2026-07-05T10:14:01Z"}],"graph_snapshots":[{"event_id":"sha256:001577ff1f949118dfff433cf2dfd9bfff43b8d26b7ed03f153054a0b9f6fd70","target":"graph","created_at":"2026-07-05T10:14:01Z","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/2303.14061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alessandra Russo, Daniel Furelos-Blanco, Leo Ardon","cross_cats":["cs.MA","cs.SC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-24T15:12:28Z","title":"Learning Reward Machines in Cooperative Multi-Agent Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14061","kind":"arxiv","version":4},"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:f6c00793ed5fe4523c53d11d2e7e00011fac73c38218ca3f7ad85b74efde6e2d","target":"record","created_at":"2026-07-05T10:14:01Z","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":"3f0f2b9cdbe40ea2c4f5efafbbbd0aed68bfcb1a4317df9e4908e0458e5e0331","cross_cats_sorted":["cs.MA","cs.SC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-24T15:12:28Z","title_canon_sha256":"d6bff939802bd3cb6ccfb03ee0a3dfe6c7f4497771a9fbdd37ed54bb8046442c"},"schema_version":"1.0","source":{"id":"2303.14061","kind":"arxiv","version":4}},"canonical_sha256":"4adc114dd1d88a5f29fc699590c7146d7db46ab27eacebde3a9f217ee76e8a5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4adc114dd1d88a5f29fc699590c7146d7db46ab27eacebde3a9f217ee76e8a5f","first_computed_at":"2026-07-05T10:14:01.249759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:01.249759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xxDh/OgXrTTY0W8h4CqkXOHnTFtlywzTBl7SenlCzaulfDL9KkCA9jHQ54a3lc0hAuCKWV1bVdl5arVWfcXdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:01.250232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.14061","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6c00793ed5fe4523c53d11d2e7e00011fac73c38218ca3f7ad85b74efde6e2d","sha256:001577ff1f949118dfff433cf2dfd9bfff43b8d26b7ed03f153054a0b9f6fd70"],"state_sha256":"d8710beec1168b966f1cac68f27326d24297ea653deedd6f725c20fdac81da6c"}