{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:L4FFMGABSAK7DHLE4ZV3TFNQMS","short_pith_number":"pith:L4FFMGAB","schema_version":"1.0","canonical_sha256":"5f0a5618019015f19d64e66bb995b06496f2fe7b76df43ec50c7530396dd7adb","source":{"kind":"arxiv","id":"1711.10173","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Policy Search via Return-Weighted Density Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Masashi Sugiyama, Takayuki Osa","submitted_at":"2017-11-28T08:30:11Z","abstract_excerpt":"Learning an optimal policy from a multi-modal reward function is a challenging problem in reinforcement learning (RL). Hierarchical RL (HRL) tackles this problem by learning a hierarchical policy, where multiple option policies are in charge of different strategies corresponding to modes of a reward function and a gating policy selects the best option for a given context. Although HRL has been demonstrated to be promising, current state-of-the-art methods cannot still perform well in complex real-world problems due to the difficulty of identifying modes of the reward function. In this paper, w"},"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":"1711.10173","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T08:30:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"12c119a611225277eace2ee0fa74b9fab05fd4406488d41af1331482f38f5a52","abstract_canon_sha256":"f654785916bf8e2348328090c346b2f55a5e48a0df8fe7e275fdd6060cd0feb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:12.713486Z","signature_b64":"hMf2E7W+Y3qIgloA7MY2kFppzAB3tAc6i1R/vZof0DcnDSMFcCeHjm6PvaUodyrdHQi0Ko+sTbYQpR2yIoYvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f0a5618019015f19d64e66bb995b06496f2fe7b76df43ec50c7530396dd7adb","last_reissued_at":"2026-05-18T00:29:12.712853Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:12.712853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Policy Search via Return-Weighted Density Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Masashi Sugiyama, Takayuki Osa","submitted_at":"2017-11-28T08:30:11Z","abstract_excerpt":"Learning an optimal policy from a multi-modal reward function is a challenging problem in reinforcement learning (RL). Hierarchical RL (HRL) tackles this problem by learning a hierarchical policy, where multiple option policies are in charge of different strategies corresponding to modes of a reward function and a gating policy selects the best option for a given context. Although HRL has been demonstrated to be promising, current state-of-the-art methods cannot still perform well in complex real-world problems due to the difficulty of identifying modes of the reward function. In this paper, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10173","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1711.10173","created_at":"2026-05-18T00:29:12.712949+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.10173v2","created_at":"2026-05-18T00:29:12.712949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10173","created_at":"2026-05-18T00:29:12.712949+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4FFMGABSAK7","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4FFMGABSAK7DHLE","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4FFMGAB","created_at":"2026-05-18T12:31:28.150371+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/L4FFMGABSAK7DHLE4ZV3TFNQMS","json":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS.json","graph_json":"https://pith.science/api/pith-number/L4FFMGABSAK7DHLE4ZV3TFNQMS/graph.json","events_json":"https://pith.science/api/pith-number/L4FFMGABSAK7DHLE4ZV3TFNQMS/events.json","paper":"https://pith.science/paper/L4FFMGAB"},"agent_actions":{"view_html":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS","download_json":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS.json","view_paper":"https://pith.science/paper/L4FFMGAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.10173&json=true","fetch_graph":"https://pith.science/api/pith-number/L4FFMGABSAK7DHLE4ZV3TFNQMS/graph.json","fetch_events":"https://pith.science/api/pith-number/L4FFMGABSAK7DHLE4ZV3TFNQMS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS/action/storage_attestation","attest_author":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS/action/author_attestation","sign_citation":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS/action/citation_signature","submit_replication":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS/action/replication_record"}},"created_at":"2026-05-18T00:29:12.712949+00:00","updated_at":"2026-05-18T00:29:12.712949+00:00"}