{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TGAGKRSPMHJI76ZFWPCFNRDICY","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":"c99a74ee5eabad5a65e1f23a43f55d6888cff2fa7cb6d045346355d03e270c2c","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-08-21T08:22:11Z","title_canon_sha256":"f7d6220382b937d6d6bc6ea3e9caf74cf3960f5a7705e0041c94d006cf4af089"},"schema_version":"1.0","source":{"id":"2408.11416","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11416","created_at":"2026-07-05T08:57:43Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11416v1","created_at":"2026-07-05T08:57:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11416","created_at":"2026-07-05T08:57:43Z"},{"alias_kind":"pith_short_12","alias_value":"TGAGKRSPMHJI","created_at":"2026-07-05T08:57:43Z"},{"alias_kind":"pith_short_16","alias_value":"TGAGKRSPMHJI76ZF","created_at":"2026-07-05T08:57:43Z"},{"alias_kind":"pith_short_8","alias_value":"TGAGKRSP","created_at":"2026-07-05T08:57:43Z"}],"graph_snapshots":[{"event_id":"sha256:765491df111f11ef45d862492c73c4f6bf305b05182975907510ee6b0e4c92c3","target":"graph","created_at":"2026-07-05T08:57:43Z","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/2408.11416/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in reinforcement learning have made significant impacts across various domains, yet they often struggle in complex multi-agent environments due to issues like algorithm instability, low sampling efficiency, and the challenges of exploration and dimensionality explosion. Hierarchical reinforcement learning (HRL) offers a structured approach to decompose complex tasks into simpler sub-tasks, which is promising for multi-agent settings. This paper advances the field by introducing a hierarchical architecture that autonomously generates effective subgoals without explicit const","authors_text":"Changtian Zhang, Cheng Xu, Ran Wang, Shihong Duan, Xiaotong Zhang, Yadong Wan, Yuchen Shi","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-08-21T08:22:11Z","title":"Subgoal-based Hierarchical Reinforcement Learning for Multi-Agent Collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11416","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":"sha256:601668f21b0577df08b1e87715ee7cb28a4ae393b69af710e267246a5dff590d","target":"record","created_at":"2026-07-05T08:57:43Z","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":"c99a74ee5eabad5a65e1f23a43f55d6888cff2fa7cb6d045346355d03e270c2c","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-08-21T08:22:11Z","title_canon_sha256":"f7d6220382b937d6d6bc6ea3e9caf74cf3960f5a7705e0041c94d006cf4af089"},"schema_version":"1.0","source":{"id":"2408.11416","kind":"arxiv","version":1}},"canonical_sha256":"998065464f61d28ffb25b3c456c468163c2788f6edc8ea06990e69ee9732b96e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"998065464f61d28ffb25b3c456c468163c2788f6edc8ea06990e69ee9732b96e","first_computed_at":"2026-07-05T08:57:43.710013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:43.710013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"evizC8o+rpNiuUel13S+ppSzH1A8ogKncDZYl17XwwEoWN60UZIUt71nE5sQW84nwuqhHkIPce2sO+kffvsMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:43.710498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11416","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:601668f21b0577df08b1e87715ee7cb28a4ae393b69af710e267246a5dff590d","sha256:765491df111f11ef45d862492c73c4f6bf305b05182975907510ee6b0e4c92c3"],"state_sha256":"a2effefb2dce7568517e814ab3463a7914b5537381f651a68544cee97ac22d7a"}