{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MPWDJF4HLXAGNXH2WBYH5NGNHB","short_pith_number":"pith:MPWDJF4H","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"},"canonical_sha256":"63ec3497875dc066dcfab0707eb4cd385fce791dd0a91d0e61889315b2f287e3","source":{"kind":"arxiv","id":"1912.03558","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.03558","created_at":"2026-07-05T01:01:22Z"},{"alias_kind":"arxiv_version","alias_value":"1912.03558v3","created_at":"2026-07-05T01:01:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03558","created_at":"2026-07-05T01:01:22Z"},{"alias_kind":"pith_short_12","alias_value":"MPWDJF4HLXAG","created_at":"2026-07-05T01:01:22Z"},{"alias_kind":"pith_short_16","alias_value":"MPWDJF4HLXAGNXH2","created_at":"2026-07-05T01:01:22Z"},{"alias_kind":"pith_short_8","alias_value":"MPWDJF4H","created_at":"2026-07-05T01:01:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MPWDJF4HLXAGNXH2WBYH5NGNHB","target":"record","payload":{"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"},"canonical_sha256":"63ec3497875dc066dcfab0707eb4cd385fce791dd0a91d0e61889315b2f287e3","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"},"source_kind":"arxiv","source_id":"1912.03558","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:01:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g/Xaz3GGN15DlIHTjlVLh439xuIiFGmvGaqcKjSHanVnMJVtKqizoJ7OpL3TFWpYw3YxU78X29f1796x1inmCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:00:16.699523Z"},"content_sha256":"731a380e5e0bc07bed1df477fd81b24d704271351872ca11cdefa9f2b9753448","schema_version":"1.0","event_id":"sha256:731a380e5e0bc07bed1df477fd81b24d704271351872ca11cdefa9f2b9753448"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MPWDJF4HLXAGNXH2WBYH5NGNHB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:01:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Us2EHzV8adE7mwyBxze3pPACxX0wjvRkizpD2dNwQx+rasyK2GxwW76prnoodpfaK4B4J/6iW6dp16ElEg7hDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:00:16.700037Z"},"content_sha256":"f3c3fed6770030cbb9edbd753f7c8ffb2f891095431e04688f28a6e8cff60843","schema_version":"1.0","event_id":"sha256:f3c3fed6770030cbb9edbd753f7c8ffb2f891095431e04688f28a6e8cff60843"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB/bundle.json","state_url":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T03:00:16Z","links":{"resolver":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB","bundle":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB/bundle.json","state":"https://pith.science/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MPWDJF4HLXAGNXH2WBYH5NGNHB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MPWDJF4HLXAGNXH2WBYH5NGNHB","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":"3a14c67349afbe43387fa82f44e0976ca71ec9679378d90a34b40ba4c87fb9b1","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-07T20:41:32Z","title_canon_sha256":"8b327268ae2b319c927b39c543584df09dcb9f37607d4bc1355c3edb9caf7e00"},"schema_version":"1.0","source":{"id":"1912.03558","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.03558","created_at":"2026-07-05T01:01:22Z"},{"alias_kind":"arxiv_version","alias_value":"1912.03558v3","created_at":"2026-07-05T01:01:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.03558","created_at":"2026-07-05T01:01:22Z"},{"alias_kind":"pith_short_12","alias_value":"MPWDJF4HLXAG","created_at":"2026-07-05T01:01:22Z"},{"alias_kind":"pith_short_16","alias_value":"MPWDJF4HLXAGNXH2","created_at":"2026-07-05T01:01:22Z"},{"alias_kind":"pith_short_8","alias_value":"MPWDJF4H","created_at":"2026-07-05T01:01:22Z"}],"graph_snapshots":[{"event_id":"sha256:f3c3fed6770030cbb9edbd753f7c8ffb2f891095431e04688f28a6e8cff60843","target":"graph","created_at":"2026-07-05T01:01:22Z","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/1912.03558/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hongyuan Zha, Igor Borovikov, Jiachen Yang","cross_cats":["cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-07T20:41:32Z","title":"Hierarchical Cooperative Multi-Agent Reinforcement Learning with Skill Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.03558","kind":"arxiv","version":3},"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":"sha256:731a380e5e0bc07bed1df477fd81b24d704271351872ca11cdefa9f2b9753448","target":"record","created_at":"2026-07-05T01:01:22Z","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":"3a14c67349afbe43387fa82f44e0976ca71ec9679378d90a34b40ba4c87fb9b1","cross_cats_sorted":["cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-07T20:41:32Z","title_canon_sha256":"8b327268ae2b319c927b39c543584df09dcb9f37607d4bc1355c3edb9caf7e00"},"schema_version":"1.0","source":{"id":"1912.03558","kind":"arxiv","version":3}},"canonical_sha256":"63ec3497875dc066dcfab0707eb4cd385fce791dd0a91d0e61889315b2f287e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63ec3497875dc066dcfab0707eb4cd385fce791dd0a91d0e61889315b2f287e3","first_computed_at":"2026-07-05T01:01:22.456331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:01:22.456331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kTEZTWLf5JhP6msvXcvN6pwSUpJP95mVdHvelFCIdm3GuLUDTlmhSnCuDuwl5THBloxF+/r1afV+GK1fOEYTCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:01:22.456897Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.03558","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:731a380e5e0bc07bed1df477fd81b24d704271351872ca11cdefa9f2b9753448","sha256:f3c3fed6770030cbb9edbd753f7c8ffb2f891095431e04688f28a6e8cff60843"],"state_sha256":"ef0408eb61aec424489abb3aba3b5c13cb385e8a4ab5fe1d80261a35e0779970"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YBwA+8PZaDaiULFtphPMSIdr42iDh6asxGm4kPG3kfd4tKKzRc0ad8mFQiipPmOdHFt12HF3f3XxQS4MNaBfDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:00:16.705716Z","bundle_sha256":"9d37f56418737eddf77bfd116e006632e841629accb891b066678cc8e219779c"}}