{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6U4UL53MILDOERVCJA2DMNHUVA","short_pith_number":"pith:6U4UL53M","schema_version":"1.0","canonical_sha256":"f53945f76c42c6e246a248343634f4a83528ea494d59047560608061fe58589f","source":{"kind":"arxiv","id":"2103.12192","version":2},"attestation_state":"computed","paper":{"title":"Reward-Reinforced Reinforcement Learning for Multi-agent Systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Antonio Garcia-Dominguez, Changgang Zheng, Juan Parra-Ullauri, Nelly Bencomo, Shufan Yang","submitted_at":"2021-03-22T21:50:09Z","abstract_excerpt":"Reinforcement learning algorithms in multi-agent systems deliver highly resilient and adaptable solutions for common problems in telecommunications,aerospace, and industrial robotics. However, achieving an optimal global goal remains a persistent obstacle for collaborative multi-agent systems, where learning affects the behaviour of more than one agent. A number of nonlinear function approximation methods have been proposed for solving the Bellman equation, which describe a recursive format of an optimal policy. However, how to leverage the value distribution based on reinforcement learning, a"},"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":"2103.12192","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2021-03-22T21:50:09Z","cross_cats_sorted":[],"title_canon_sha256":"cf6d31571192ab641ffb0883549392eb28be3bfb284d9743276d640715192cc5","abstract_canon_sha256":"13a71de4006883481247b4922323faef5d3142f07a528de9f224b254bc020214"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:33.465510Z","signature_b64":"mqZBpwoxKsv8kvM2FoI/iA2KRfXhLmUfw+4WuH3qhepu/yNqPbB1P0PUmvIrGml8jHaJmLTsO0FUJMqA+lnlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f53945f76c42c6e246a248343634f4a83528ea494d59047560608061fe58589f","last_reissued_at":"2026-07-05T02:40:33.465080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:33.465080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward-Reinforced Reinforcement Learning for Multi-agent Systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Antonio Garcia-Dominguez, Changgang Zheng, Juan Parra-Ullauri, Nelly Bencomo, Shufan Yang","submitted_at":"2021-03-22T21:50:09Z","abstract_excerpt":"Reinforcement learning algorithms in multi-agent systems deliver highly resilient and adaptable solutions for common problems in telecommunications,aerospace, and industrial robotics. However, achieving an optimal global goal remains a persistent obstacle for collaborative multi-agent systems, where learning affects the behaviour of more than one agent. A number of nonlinear function approximation methods have been proposed for solving the Bellman equation, which describe a recursive format of an optimal policy. However, how to leverage the value distribution based on reinforcement learning, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12192","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/2103.12192/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":"2103.12192","created_at":"2026-07-05T02:40:33.465137+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.12192v2","created_at":"2026-07-05T02:40:33.465137+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12192","created_at":"2026-07-05T02:40:33.465137+00:00"},{"alias_kind":"pith_short_12","alias_value":"6U4UL53MILDO","created_at":"2026-07-05T02:40:33.465137+00:00"},{"alias_kind":"pith_short_16","alias_value":"6U4UL53MILDOERVC","created_at":"2026-07-05T02:40:33.465137+00:00"},{"alias_kind":"pith_short_8","alias_value":"6U4UL53M","created_at":"2026-07-05T02:40:33.465137+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/6U4UL53MILDOERVCJA2DMNHUVA","json":"https://pith.science/pith/6U4UL53MILDOERVCJA2DMNHUVA.json","graph_json":"https://pith.science/api/pith-number/6U4UL53MILDOERVCJA2DMNHUVA/graph.json","events_json":"https://pith.science/api/pith-number/6U4UL53MILDOERVCJA2DMNHUVA/events.json","paper":"https://pith.science/paper/6U4UL53M"},"agent_actions":{"view_html":"https://pith.science/pith/6U4UL53MILDOERVCJA2DMNHUVA","download_json":"https://pith.science/pith/6U4UL53MILDOERVCJA2DMNHUVA.json","view_paper":"https://pith.science/paper/6U4UL53M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.12192&json=true","fetch_graph":"https://pith.science/api/pith-number/6U4UL53MILDOERVCJA2DMNHUVA/graph.json","fetch_events":"https://pith.science/api/pith-number/6U4UL53MILDOERVCJA2DMNHUVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6U4UL53MILDOERVCJA2DMNHUVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6U4UL53MILDOERVCJA2DMNHUVA/action/storage_attestation","attest_author":"https://pith.science/pith/6U4UL53MILDOERVCJA2DMNHUVA/action/author_attestation","sign_citation":"https://pith.science/pith/6U4UL53MILDOERVCJA2DMNHUVA/action/citation_signature","submit_replication":"https://pith.science/pith/6U4UL53MILDOERVCJA2DMNHUVA/action/replication_record"}},"created_at":"2026-07-05T02:40:33.465137+00:00","updated_at":"2026-07-05T02:40:33.465137+00:00"}