{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UAGSDGML475SUQJBLLEEGXMHHT","short_pith_number":"pith:UAGSDGML","schema_version":"1.0","canonical_sha256":"a00d21998be7fb2a41215ac8435d873ccd1948d6cbb4aa31255c6f9f4ed2e253","source":{"kind":"arxiv","id":"2507.06690","version":1},"attestation_state":"computed","paper":{"title":"Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Guobin Zhu, Hongyin Zhang, Rui Zhou, Shiyu Zhao, Wenkang Ji","submitted_at":"2025-07-09T09:34:41Z","abstract_excerpt":"Multi-task multi-agent reinforcement learning (MT-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challenging for existing multi-task learning methods to handle complex problems, as they are unable to handle unrelated tasks and possess limited knowledge transfer capabilities. In this paper, we propose a hierarchical approach that efficiently addresses these challenges. The high-level module utilizes a skill graph, while the low-level module employs a standard MARL algorithm. Our approach offers two contributions. First,"},"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":"2507.06690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-07-09T09:34:41Z","cross_cats_sorted":[],"title_canon_sha256":"31eaa4643d656215d2eba71cce6fa096f297cce558045b8a1c2c6fd96fcabd35","abstract_canon_sha256":"73d080f8304ff4e5eaaee1d2c43a017a789ce5c369051d697b73f496f4ea557b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:21.367124Z","signature_b64":"rOc6k2A5sN9k3yB2A/1tfZWgMy/xp0WqDXkTa+s35ly8Si+DHQRDZr0ZYPYOdMuf2PpnR6M35FS42bs0zl2cDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a00d21998be7fb2a41215ac8435d873ccd1948d6cbb4aa31255c6f9f4ed2e253","last_reissued_at":"2026-07-05T11:34:21.366510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:21.366510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Multi-Agent Reinforcement Learning via Skill Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Donglin Wang, Guobin Zhu, Hongyin Zhang, Rui Zhou, Shiyu Zhao, Wenkang Ji","submitted_at":"2025-07-09T09:34:41Z","abstract_excerpt":"Multi-task multi-agent reinforcement learning (MT-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challenging for existing multi-task learning methods to handle complex problems, as they are unable to handle unrelated tasks and possess limited knowledge transfer capabilities. In this paper, we propose a hierarchical approach that efficiently addresses these challenges. The high-level module utilizes a skill graph, while the low-level module employs a standard MARL algorithm. Our approach offers two contributions. First,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06690","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/2507.06690/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":"2507.06690","created_at":"2026-07-05T11:34:21.366578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06690v1","created_at":"2026-07-05T11:34:21.366578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06690","created_at":"2026-07-05T11:34:21.366578+00:00"},{"alias_kind":"pith_short_12","alias_value":"UAGSDGML475S","created_at":"2026-07-05T11:34:21.366578+00:00"},{"alias_kind":"pith_short_16","alias_value":"UAGSDGML475SUQJB","created_at":"2026-07-05T11:34:21.366578+00:00"},{"alias_kind":"pith_short_8","alias_value":"UAGSDGML","created_at":"2026-07-05T11:34:21.366578+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/UAGSDGML475SUQJBLLEEGXMHHT","json":"https://pith.science/pith/UAGSDGML475SUQJBLLEEGXMHHT.json","graph_json":"https://pith.science/api/pith-number/UAGSDGML475SUQJBLLEEGXMHHT/graph.json","events_json":"https://pith.science/api/pith-number/UAGSDGML475SUQJBLLEEGXMHHT/events.json","paper":"https://pith.science/paper/UAGSDGML"},"agent_actions":{"view_html":"https://pith.science/pith/UAGSDGML475SUQJBLLEEGXMHHT","download_json":"https://pith.science/pith/UAGSDGML475SUQJBLLEEGXMHHT.json","view_paper":"https://pith.science/paper/UAGSDGML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06690&json=true","fetch_graph":"https://pith.science/api/pith-number/UAGSDGML475SUQJBLLEEGXMHHT/graph.json","fetch_events":"https://pith.science/api/pith-number/UAGSDGML475SUQJBLLEEGXMHHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UAGSDGML475SUQJBLLEEGXMHHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UAGSDGML475SUQJBLLEEGXMHHT/action/storage_attestation","attest_author":"https://pith.science/pith/UAGSDGML475SUQJBLLEEGXMHHT/action/author_attestation","sign_citation":"https://pith.science/pith/UAGSDGML475SUQJBLLEEGXMHHT/action/citation_signature","submit_replication":"https://pith.science/pith/UAGSDGML475SUQJBLLEEGXMHHT/action/replication_record"}},"created_at":"2026-07-05T11:34:21.366578+00:00","updated_at":"2026-07-05T11:34:21.366578+00:00"}