{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z276OLFL3L6GYCSX5O6GE7YC53","short_pith_number":"pith:Z276OLFL","schema_version":"1.0","canonical_sha256":"cebfe72cabdafc6c0a57ebbc627f02eedafdd86e524000fcc8f26971852161a4","source":{"kind":"arxiv","id":"2205.15716","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Learning of Numerical Methods for Hyperbolic PDEs with Factored Dec-MDP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Dheeraj S.K. Kapilavai, Elliot Way, Yiwei Fu","submitted_at":"2022-05-31T12:02:18Z","abstract_excerpt":"Factored decentralized Markov decision process (Dec-MDP) is a framework for modeling sequential decision making problems in multi-agent systems. In this paper, we formalize the learning of numerical methods for hyperbolic partial differential equations (PDEs), specifically the Weighted Essentially Non-Oscillatory (WENO) scheme, as a factored Dec-MDP problem. We show that different reward formulations lead to either reinforcement learning (RL) or behavior cloning, and a homogeneous policy could be learned for all agents under the RL formulation with a policy gradient algorithm. Because the trai"},"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":"2205.15716","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-31T12:02:18Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"26d3c32e889b7a743b6ff323d799cf8da0bdf78d63c150c2190fa29fa365d90f","abstract_canon_sha256":"ee89be3ee31275ce06f0b607a40bcc052f4e2161f673126f66a18ef8e0dcf728"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:31.895548Z","signature_b64":"n67gosg26FOjipKHq/8ihPZlAb6DxJz7ctptjijajVCyhWaQIDl7sTejD2E7cO2Db7tOD7Q6o35D/UTiWidtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cebfe72cabdafc6c0a57ebbc627f02eedafdd86e524000fcc8f26971852161a4","last_reissued_at":"2026-07-05T05:06:31.895095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:31.895095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Learning of Numerical Methods for Hyperbolic PDEs with Factored Dec-MDP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Dheeraj S.K. Kapilavai, Elliot Way, Yiwei Fu","submitted_at":"2022-05-31T12:02:18Z","abstract_excerpt":"Factored decentralized Markov decision process (Dec-MDP) is a framework for modeling sequential decision making problems in multi-agent systems. In this paper, we formalize the learning of numerical methods for hyperbolic partial differential equations (PDEs), specifically the Weighted Essentially Non-Oscillatory (WENO) scheme, as a factored Dec-MDP problem. We show that different reward formulations lead to either reinforcement learning (RL) or behavior cloning, and a homogeneous policy could be learned for all agents under the RL formulation with a policy gradient algorithm. Because the trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15716","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/2205.15716/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":"2205.15716","created_at":"2026-07-05T05:06:31.895152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.15716v1","created_at":"2026-07-05T05:06:31.895152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15716","created_at":"2026-07-05T05:06:31.895152+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z276OLFL3L6G","created_at":"2026-07-05T05:06:31.895152+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z276OLFL3L6GYCSX","created_at":"2026-07-05T05:06:31.895152+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z276OLFL","created_at":"2026-07-05T05:06:31.895152+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/Z276OLFL3L6GYCSX5O6GE7YC53","json":"https://pith.science/pith/Z276OLFL3L6GYCSX5O6GE7YC53.json","graph_json":"https://pith.science/api/pith-number/Z276OLFL3L6GYCSX5O6GE7YC53/graph.json","events_json":"https://pith.science/api/pith-number/Z276OLFL3L6GYCSX5O6GE7YC53/events.json","paper":"https://pith.science/paper/Z276OLFL"},"agent_actions":{"view_html":"https://pith.science/pith/Z276OLFL3L6GYCSX5O6GE7YC53","download_json":"https://pith.science/pith/Z276OLFL3L6GYCSX5O6GE7YC53.json","view_paper":"https://pith.science/paper/Z276OLFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.15716&json=true","fetch_graph":"https://pith.science/api/pith-number/Z276OLFL3L6GYCSX5O6GE7YC53/graph.json","fetch_events":"https://pith.science/api/pith-number/Z276OLFL3L6GYCSX5O6GE7YC53/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z276OLFL3L6GYCSX5O6GE7YC53/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z276OLFL3L6GYCSX5O6GE7YC53/action/storage_attestation","attest_author":"https://pith.science/pith/Z276OLFL3L6GYCSX5O6GE7YC53/action/author_attestation","sign_citation":"https://pith.science/pith/Z276OLFL3L6GYCSX5O6GE7YC53/action/citation_signature","submit_replication":"https://pith.science/pith/Z276OLFL3L6GYCSX5O6GE7YC53/action/replication_record"}},"created_at":"2026-07-05T05:06:31.895152+00:00","updated_at":"2026-07-05T05:06:31.895152+00:00"}