{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6U4UL53MILDOERVCJA2DMNHUVA","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":"13a71de4006883481247b4922323faef5d3142f07a528de9f224b254bc020214","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2021-03-22T21:50:09Z","title_canon_sha256":"cf6d31571192ab641ffb0883549392eb28be3bfb284d9743276d640715192cc5"},"schema_version":"1.0","source":{"id":"2103.12192","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12192","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12192v2","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12192","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"pith_short_12","alias_value":"6U4UL53MILDO","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"pith_short_16","alias_value":"6U4UL53MILDOERVC","created_at":"2026-07-05T02:40:33Z"},{"alias_kind":"pith_short_8","alias_value":"6U4UL53M","created_at":"2026-07-05T02:40:33Z"}],"graph_snapshots":[{"event_id":"sha256:837b44e37e5351f13ff5d1253d82beca1e82542faf2e1cb69bc1521cffbe1d8b","target":"graph","created_at":"2026-07-05T02:40:33Z","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/2103.12192/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Antonio Garcia-Dominguez, Changgang Zheng, Juan Parra-Ullauri, Nelly Bencomo, Shufan Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2021-03-22T21:50:09Z","title":"Reward-Reinforced Reinforcement Learning for Multi-agent Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12192","kind":"arxiv","version":2},"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":"sha256:8f45ad97d45519eb0da4958e7bd0e0e46aecb4151ca5f1945e93aed968d04e0e","target":"record","created_at":"2026-07-05T02:40:33Z","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":"13a71de4006883481247b4922323faef5d3142f07a528de9f224b254bc020214","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2021-03-22T21:50:09Z","title_canon_sha256":"cf6d31571192ab641ffb0883549392eb28be3bfb284d9743276d640715192cc5"},"schema_version":"1.0","source":{"id":"2103.12192","kind":"arxiv","version":2}},"canonical_sha256":"f53945f76c42c6e246a248343634f4a83528ea494d59047560608061fe58589f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f53945f76c42c6e246a248343634f4a83528ea494d59047560608061fe58589f","first_computed_at":"2026-07-05T02:40:33.465080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:33.465080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mqZBpwoxKsv8kvM2FoI/iA2KRfXhLmUfw+4WuH3qhepu/yNqPbB1P0PUmvIrGml8jHaJmLTsO0FUJMqA+lnlBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:33.465510Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.12192","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f45ad97d45519eb0da4958e7bd0e0e46aecb4151ca5f1945e93aed968d04e0e","sha256:837b44e37e5351f13ff5d1253d82beca1e82542faf2e1cb69bc1521cffbe1d8b"],"state_sha256":"fbea9f4bf43fa94581b9f8bcdd769f576fd7c56745b102ed6f8a16bea9550da4"}