{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MTKMO2DRML2MGP2I2V472FFS3V","short_pith_number":"pith:MTKMO2DR","schema_version":"1.0","canonical_sha256":"64d4c7687162f4c33f48d579fd14b2dd536ab1640e6127b3e37a81a5d06db6c8","source":{"kind":"arxiv","id":"2503.17803","version":1},"attestation_state":"computed","paper":{"title":"A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And Inference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ME"],"primary_cat":"cs.LG","authors_text":"Franco Zambonelli, Giovanni Briglia, Stefano Mariani","submitted_at":"2025-03-22T15:49:13Z","abstract_excerpt":"Causal reasoning is increasingly used in Reinforcement Learning (RL) to improve the learning process in several dimensions: efficacy of learned policies, efficiency of convergence, generalisation capabilities, safety and interpretability of behaviour. However, applications of causal reasoning to Multi-Agent RL (MARL) are still mostly unexplored. In this paper, we take the first step in investigating the opportunities and challenges of applying causal reasoning in MARL. We measure the impact of a simple form of causal augmentation in state-of-the-art MARL scenarios increasingly requiring cooper"},"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":"2503.17803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-22T15:49:13Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ME"],"title_canon_sha256":"d96e49c5b8aadf94a6824ae66e4d2bec7dc80db08da8f78710bd8b05e76b74b9","abstract_canon_sha256":"41cd2af4d7a76d8c597cb9b7b4254fbc58949945b412a40d876c2f1db64dd6ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:55.203096Z","signature_b64":"DoWtXbGW69rKiu/JFOhQcNv6/2FpNB33NHQdHlAHsOHHShflUvR0m8W8+VgFV1i6vABbmCmF3Ky0MEuJ/rqWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64d4c7687162f4c33f48d579fd14b2dd536ab1640e6127b3e37a81a5d06db6c8","last_reissued_at":"2026-07-05T10:37:55.202483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:55.202483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Roadmap Towards Improving Multi-Agent Reinforcement Learning With Causal Discovery And Inference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ME"],"primary_cat":"cs.LG","authors_text":"Franco Zambonelli, Giovanni Briglia, Stefano Mariani","submitted_at":"2025-03-22T15:49:13Z","abstract_excerpt":"Causal reasoning is increasingly used in Reinforcement Learning (RL) to improve the learning process in several dimensions: efficacy of learned policies, efficiency of convergence, generalisation capabilities, safety and interpretability of behaviour. However, applications of causal reasoning to Multi-Agent RL (MARL) are still mostly unexplored. In this paper, we take the first step in investigating the opportunities and challenges of applying causal reasoning in MARL. We measure the impact of a simple form of causal augmentation in state-of-the-art MARL scenarios increasingly requiring cooper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17803","kind":"arxiv","version":1},"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/2503.17803/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":"2503.17803","created_at":"2026-07-05T10:37:55.202554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17803v1","created_at":"2026-07-05T10:37:55.202554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17803","created_at":"2026-07-05T10:37:55.202554+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTKMO2DRML2M","created_at":"2026-07-05T10:37:55.202554+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTKMO2DRML2MGP2I","created_at":"2026-07-05T10:37:55.202554+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTKMO2DR","created_at":"2026-07-05T10:37:55.202554+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/MTKMO2DRML2MGP2I2V472FFS3V","json":"https://pith.science/pith/MTKMO2DRML2MGP2I2V472FFS3V.json","graph_json":"https://pith.science/api/pith-number/MTKMO2DRML2MGP2I2V472FFS3V/graph.json","events_json":"https://pith.science/api/pith-number/MTKMO2DRML2MGP2I2V472FFS3V/events.json","paper":"https://pith.science/paper/MTKMO2DR"},"agent_actions":{"view_html":"https://pith.science/pith/MTKMO2DRML2MGP2I2V472FFS3V","download_json":"https://pith.science/pith/MTKMO2DRML2MGP2I2V472FFS3V.json","view_paper":"https://pith.science/paper/MTKMO2DR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17803&json=true","fetch_graph":"https://pith.science/api/pith-number/MTKMO2DRML2MGP2I2V472FFS3V/graph.json","fetch_events":"https://pith.science/api/pith-number/MTKMO2DRML2MGP2I2V472FFS3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTKMO2DRML2MGP2I2V472FFS3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTKMO2DRML2MGP2I2V472FFS3V/action/storage_attestation","attest_author":"https://pith.science/pith/MTKMO2DRML2MGP2I2V472FFS3V/action/author_attestation","sign_citation":"https://pith.science/pith/MTKMO2DRML2MGP2I2V472FFS3V/action/citation_signature","submit_replication":"https://pith.science/pith/MTKMO2DRML2MGP2I2V472FFS3V/action/replication_record"}},"created_at":"2026-07-05T10:37:55.202554+00:00","updated_at":"2026-07-05T10:37:55.202554+00:00"}