{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SSBVJ2VRFGZTNZJ5BRXB6N27HJ","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":"06a2c72b7cc06cd946323a4d06f2c3577cb84a739319d697b28c0f66e64064ce","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-11T14:22:10Z","title_canon_sha256":"376a7c7c3ad9c09bceda4fec285d1e0f5ec771926f6ae0203dd226bffcb51ea2"},"schema_version":"1.0","source":{"id":"2501.06554","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06554","created_at":"2026-07-05T10:00:28Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06554v1","created_at":"2026-07-05T10:00:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06554","created_at":"2026-07-05T10:00:28Z"},{"alias_kind":"pith_short_12","alias_value":"SSBVJ2VRFGZT","created_at":"2026-07-05T10:00:28Z"},{"alias_kind":"pith_short_16","alias_value":"SSBVJ2VRFGZTNZJ5","created_at":"2026-07-05T10:00:28Z"},{"alias_kind":"pith_short_8","alias_value":"SSBVJ2VR","created_at":"2026-07-05T10:00:28Z"}],"graph_snapshots":[{"event_id":"sha256:102312c70f3063593346816fbf3a6f541abf957881f307410d71fad557955d17","target":"graph","created_at":"2026-07-05T10:00:28Z","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/2501.06554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a hierarchical reinforcement learning (RL) approach to address the agent grouping or pairing problem in cooperative multi-agent systems. The goal is to simultaneously learn the optimal grouping and agent policy. By employing a hierarchical RL framework, we distinguish between high-level decisions of grouping and low-level agents' actions. Our approach utilizes the CTDE (Centralized Training with Decentralized Execution) paradigm, ensuring efficient learning and scalable execution. We incorporate permutation-invariant neural networks to handle the homogeneity and cooperation","authors_text":"Liyuan Hu","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-11T14:22:10Z","title":"Hierarchical Reinforcement Learning for Optimal Agent Grouping in Cooperative Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06554","kind":"arxiv","version":1},"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":"sha256:942508a86dbb3021649424a45abeba1c85603a72e8a803275909643b2fe0e824","target":"record","created_at":"2026-07-05T10:00:28Z","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":"06a2c72b7cc06cd946323a4d06f2c3577cb84a739319d697b28c0f66e64064ce","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-11T14:22:10Z","title_canon_sha256":"376a7c7c3ad9c09bceda4fec285d1e0f5ec771926f6ae0203dd226bffcb51ea2"},"schema_version":"1.0","source":{"id":"2501.06554","kind":"arxiv","version":1}},"canonical_sha256":"948354eab129b336e53d0c6e1f375f3a578b5d292809b3d34f372e17df98e764","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"948354eab129b336e53d0c6e1f375f3a578b5d292809b3d34f372e17df98e764","first_computed_at":"2026-07-05T10:00:28.089288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:28.089288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jD1VhfaF/HlyTQkf0ts7o3gR+cIoVmDNtL9ptGXdmfwxTuM3QACdYIOgFX5Uwm0nVQdZwkCRwKbbeQpFN4hkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:28.089803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06554","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:942508a86dbb3021649424a45abeba1c85603a72e8a803275909643b2fe0e824","sha256:102312c70f3063593346816fbf3a6f541abf957881f307410d71fad557955d17"],"state_sha256":"89d6d73fa8623f15f843eb20f50a0e1b1c23029017bbddf3d031acc6bdfe2a5f"}