{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MPWDJF4HLXAGNXH2WBYH5NGNHB","short_pith_number":"pith:MPWDJF4H","schema_version":"1.0","canonical_sha256":"63ec3497875dc066dcfab0707eb4cd385fce791dd0a91d0e61889315b2f287e3","source":{"kind":"arxiv","id":"1912.03558","version":3},"attestation_state":"computed","paper":{"title":"Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyuan Zha, Igor Borovikov, Jiachen Yang","submitted_at":"2019-12-07T20:41:32Z","abstract_excerpt":"Human players in professional team sports achieve high level coordination by dynamically choosing complementary skills and executing primitive actions to perform these skills. As a step toward creating intelligent agents with this capability for fully cooperative multi-agent settings, we propose a two-level hierarchical multi-agent reinforcement learning (MARL) algorithm with unsupervised skill discovery. Agents learn useful and distinct skills at the low level via independent Q-learning, while they learn to select complementary latent skill variables at the high level via centralized multi-ag"},"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":"1912.03558","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-07T20:41:32Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"8b327268ae2b319c927b39c543584df09dcb9f37607d4bc1355c3edb9caf7e00","abstract_canon_sha256":"3a14c67349afbe43387fa82f44e0976ca71ec9679378d90a34b40ba4c87fb9b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:22.456897Z","signature_b64":"kTEZTWLf5JhP6msvXcvN6pwSUpJP95mVdHvelFCIdm3GuLUDTlmhSnCuDuwl5THBloxF+/r1afV+GK1fOEYTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63ec3497875dc066dcfab0707eb4cd385fce791dd0a91d0e61889315b2f287e3","last_reissued_at":"2026-07-05T01:01:22.456331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:22.456331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyuan Zha, Igor Borovikov, Jiachen Yang","submitted_at":"2019-12-07T20:41:32Z","abstract_excerpt":"Human players in professional team sports achieve high level coordination by dynamically choosing complementary skills and executing primitive actions to perform these skills. As a step toward creating intelligent agents with this capability for fully cooperative multi-agent settings, we propose a two-level hierarchical multi-agent reinforcement learning (MARL) algorithm with unsupervised skill discovery. Agents learn useful and distinct skills at the low level via independent Q-learning, while they learn to select complementary latent skill variables at the high level via centralized multi-ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03558","kind":"arxiv","version":3},"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/1912.03558/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":"1912.03558","created_at":"2026-07-05T01:01:22.456413+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.03558v3","created_at":"2026-07-05T01:01:22.456413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03558","created_at":"2026-07-05T01:01:22.456413+00:00"},{"alias_kind":"pith_short_12","alias_value":"MPWDJF4HLXAG","created_at":"2026-07-05T01:01:22.456413+00:00"},{"alias_kind":"pith_short_16","alias_value":"MPWDJF4HLXAGNXH2","created_at":"2026-07-05T01:01:22.456413+00:00"},{"alias_kind":"pith_short_8","alias_value":"MPWDJF4H","created_at":"2026-07-05T01:01:22.456413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB","json":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB.json","graph_json":"https://pith.science/api/pith-number/MPWDJF4HLXAGNXH2WBYH5NGNHB/graph.json","events_json":"https://pith.science/api/pith-number/MPWDJF4HLXAGNXH2WBYH5NGNHB/events.json","paper":"https://pith.science/paper/MPWDJF4H"},"agent_actions":{"view_html":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB","download_json":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB.json","view_paper":"https://pith.science/paper/MPWDJF4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.03558&json=true","fetch_graph":"https://pith.science/api/pith-number/MPWDJF4HLXAGNXH2WBYH5NGNHB/graph.json","fetch_events":"https://pith.science/api/pith-number/MPWDJF4HLXAGNXH2WBYH5NGNHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB/action/storage_attestation","attest_author":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB/action/author_attestation","sign_citation":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB/action/citation_signature","submit_replication":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB/action/replication_record"}},"created_at":"2026-07-05T01:01:22.456413+00:00","updated_at":"2026-07-05T01:01:22.456413+00:00"}