{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PPULHOP2IIQOP5KO5HCLYBJKHX","short_pith_number":"pith:PPULHOP2","canonical_record":{"source":{"id":"1809.09332","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T06:19:22Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"f079b9487bc966b91236253a960d99f6dae589da8aab35ec1789d9afcad67b0a","abstract_canon_sha256":"38b9868e13d0d612e674ea20ccbf94586e72de7cd7f6651abc2b75a487243e8d"},"schema_version":"1.0"},"canonical_sha256":"7be8b3b9fa4220e7f54ee9c4bc052a3dfb2bdff15602ff7e81a7c60bfa34a3bb","source":{"kind":"arxiv","id":"1809.09332","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.09332","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"arxiv_version","alias_value":"1809.09332v2","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09332","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"pith_short_12","alias_value":"PPULHOP2IIQO","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PPULHOP2IIQOP5KO","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PPULHOP2","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PPULHOP2IIQOP5KO5HCLYBJKHX","target":"record","payload":{"canonical_record":{"source":{"id":"1809.09332","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T06:19:22Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"f079b9487bc966b91236253a960d99f6dae589da8aab35ec1789d9afcad67b0a","abstract_canon_sha256":"38b9868e13d0d612e674ea20ccbf94586e72de7cd7f6651abc2b75a487243e8d"},"schema_version":"1.0"},"canonical_sha256":"7be8b3b9fa4220e7f54ee9c4bc052a3dfb2bdff15602ff7e81a7c60bfa34a3bb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:31.051512Z","signature_b64":"+NlR+MvW1HA2Quf7R38ptoHocYskdG+52fZjWN04V0aV+lrxOHFnl3QvfsgBMNax+jxY6NqlKGMNxgZTZxu8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7be8b3b9fa4220e7f54ee9c4bc052a3dfb2bdff15602ff7e81a7c60bfa34a3bb","last_reissued_at":"2026-05-17T23:41:31.050366Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:31.050366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.09332","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:41:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M2TrLkGvkfkd/L+JEn+3u8Oy1oteT7ZDwU2HahH8IW2Eth0NFgWfPBYNvD5IZ3rZ8DlIW/x+zybEBoXLlvDnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T16:37:53.102272Z"},"content_sha256":"305645634d874da23b6e81f6ff3291071de2ea15867b7be42ccce9b81c0de39a","schema_version":"1.0","event_id":"sha256:305645634d874da23b6e81f6ff3291071de2ea15867b7be42ccce9b81c0de39a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PPULHOP2IIQOP5KO5HCLYBJKHX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Deep Multiagent Reinforcement Learning with Temporal Abstraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Changjie Fan, Chunxu Ren, Hangtian Jia, Hongyao Tang, Jianye Hao, Li Wang, Tangjie Lv, Yan Zheng, Yingfeng Chen, Zhaopeng Meng, Zongzhang Zhang","submitted_at":"2018-09-25T06:19:22Z","abstract_excerpt":"Multiagent reinforcement learning (MARL) is commonly considered to suffer from non-stationary environments and exponentially increasing policy space. It would be even more challenging when rewards are sparse and delayed over long trajectories. In this paper, we study hierarchical deep MARL in cooperative multiagent problems with sparse and delayed reward. With temporal abstraction, we decompose the problem into a hierarchy of different time scales and investigate how agents can learn high-level coordination based on the independent skills learned at the low level. Three hierarchical deep MARL "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09332","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:41:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MOryjvtYWTrXw6D0cQ622hPB7JQscdUwPCy7ZEDqdH8BzhOQ4ymLetIJkGnb5ikjduThewp4jENaKaZH4+PqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T16:37:53.102887Z"},"content_sha256":"464f2b4f0136ed03378aaf9ee85c343db1d51e950d21e921e2fa955756d4a611","schema_version":"1.0","event_id":"sha256:464f2b4f0136ed03378aaf9ee85c343db1d51e950d21e921e2fa955756d4a611"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPULHOP2IIQOP5KO5HCLYBJKHX/bundle.json","state_url":"https://pith.science/pith/PPULHOP2IIQOP5KO5HCLYBJKHX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPULHOP2IIQOP5KO5HCLYBJKHX/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":"2026-05-21T16:37:53Z","links":{"resolver":"https://pith.science/pith/PPULHOP2IIQOP5KO5HCLYBJKHX","bundle":"https://pith.science/pith/PPULHOP2IIQOP5KO5HCLYBJKHX/bundle.json","state":"https://pith.science/pith/PPULHOP2IIQOP5KO5HCLYBJKHX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPULHOP2IIQOP5KO5HCLYBJKHX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PPULHOP2IIQOP5KO5HCLYBJKHX","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":"38b9868e13d0d612e674ea20ccbf94586e72de7cd7f6651abc2b75a487243e8d","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T06:19:22Z","title_canon_sha256":"f079b9487bc966b91236253a960d99f6dae589da8aab35ec1789d9afcad67b0a"},"schema_version":"1.0","source":{"id":"1809.09332","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.09332","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"arxiv_version","alias_value":"1809.09332v2","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09332","created_at":"2026-05-17T23:41:31Z"},{"alias_kind":"pith_short_12","alias_value":"PPULHOP2IIQO","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PPULHOP2IIQOP5KO","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PPULHOP2","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:464f2b4f0136ed03378aaf9ee85c343db1d51e950d21e921e2fa955756d4a611","target":"graph","created_at":"2026-05-17T23:41:31Z","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"},"paper":{"abstract_excerpt":"Multiagent reinforcement learning (MARL) is commonly considered to suffer from non-stationary environments and exponentially increasing policy space. It would be even more challenging when rewards are sparse and delayed over long trajectories. In this paper, we study hierarchical deep MARL in cooperative multiagent problems with sparse and delayed reward. With temporal abstraction, we decompose the problem into a hierarchy of different time scales and investigate how agents can learn high-level coordination based on the independent skills learned at the low level. Three hierarchical deep MARL ","authors_text":"Changjie Fan, Chunxu Ren, Hangtian Jia, Hongyao Tang, Jianye Hao, Li Wang, Tangjie Lv, Yan Zheng, Yingfeng Chen, Zhaopeng Meng, Zongzhang Zhang","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T06:19:22Z","title":"Hierarchical Deep Multiagent Reinforcement Learning with Temporal Abstraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09332","kind":"arxiv","version":2},"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":"sha256:305645634d874da23b6e81f6ff3291071de2ea15867b7be42ccce9b81c0de39a","target":"record","created_at":"2026-05-17T23:41:31Z","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":"38b9868e13d0d612e674ea20ccbf94586e72de7cd7f6651abc2b75a487243e8d","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T06:19:22Z","title_canon_sha256":"f079b9487bc966b91236253a960d99f6dae589da8aab35ec1789d9afcad67b0a"},"schema_version":"1.0","source":{"id":"1809.09332","kind":"arxiv","version":2}},"canonical_sha256":"7be8b3b9fa4220e7f54ee9c4bc052a3dfb2bdff15602ff7e81a7c60bfa34a3bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7be8b3b9fa4220e7f54ee9c4bc052a3dfb2bdff15602ff7e81a7c60bfa34a3bb","first_computed_at":"2026-05-17T23:41:31.050366Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:31.050366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+NlR+MvW1HA2Quf7R38ptoHocYskdG+52fZjWN04V0aV+lrxOHFnl3QvfsgBMNax+jxY6NqlKGMNxgZTZxu8Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:31.051512Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.09332","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:305645634d874da23b6e81f6ff3291071de2ea15867b7be42ccce9b81c0de39a","sha256:464f2b4f0136ed03378aaf9ee85c343db1d51e950d21e921e2fa955756d4a611"],"state_sha256":"bc09e807615ea15f929a8b4a65c96f76e31bd2820bf0cae1067323f9b0172a15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RKXVy6vZai5NxeaLFyrDTWE5ljUFSgi5dnKNqI7JyzL1jjVy3yFTNR3Q+aqUQLl+0WxvRuyji3utBD66XTQRBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T16:37:53.105052Z","bundle_sha256":"cb1be3640da838f5e59068e789ee4175c7d40d845638b434bc171c8e349fb315"}}