{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:L4FFMGABSAK7DHLE4ZV3TFNQMS","short_pith_number":"pith:L4FFMGAB","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"},"canonical_sha256":"5f0a5618019015f19d64e66bb995b06496f2fe7b76df43ec50c7530396dd7adb","source":{"kind":"arxiv","id":"1711.10173","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.10173","created_at":"2026-05-18T00:29:12Z"},{"alias_kind":"arxiv_version","alias_value":"1711.10173v2","created_at":"2026-05-18T00:29:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10173","created_at":"2026-05-18T00:29:12Z"},{"alias_kind":"pith_short_12","alias_value":"L4FFMGABSAK7","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"L4FFMGABSAK7DHLE","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"L4FFMGAB","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:L4FFMGABSAK7DHLE4ZV3TFNQMS","target":"record","payload":{"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"},"canonical_sha256":"5f0a5618019015f19d64e66bb995b06496f2fe7b76df43ec50c7530396dd7adb","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"},"source_kind":"arxiv","source_id":"1711.10173","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":"2026-05-18T00:29:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"waXCjUbJ63xX5ctKZC3Avw7TUl+wmAwvv2a9e9bX/qztlaygJ7UYbh+r5JnPqUvTWjQr47//+dA3VkKIsMUBBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:48:41.691658Z"},"content_sha256":"c016543ad6e63534580b27164716e1ef1952174842fcd72555dc013b265532b3","schema_version":"1.0","event_id":"sha256:c016543ad6e63534580b27164716e1ef1952174842fcd72555dc013b265532b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:L4FFMGABSAK7DHLE4ZV3TFNQMS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:29:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uXbR6T4XqKioOUomJQYDIKyGxercz927xNXW1iWH7OUlaLPsSvO1Wntu3lDcL8k9kzhzWm1nG/eF6KieRMXiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:48:41.692329Z"},"content_sha256":"93cae00e98e3362fb7cf78b10c5b37e78ce772c32111c890d22e0452bce40440","schema_version":"1.0","event_id":"sha256:93cae00e98e3362fb7cf78b10c5b37e78ce772c32111c890d22e0452bce40440"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS/bundle.json","state_url":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS/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":"2026-05-26T11:48:41Z","links":{"resolver":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS","bundle":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS/bundle.json","state":"https://pith.science/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L4FFMGABSAK7DHLE4ZV3TFNQMS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:L4FFMGABSAK7DHLE4ZV3TFNQMS","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":"f654785916bf8e2348328090c346b2f55a5e48a0df8fe7e275fdd6060cd0feb5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T08:30:11Z","title_canon_sha256":"12c119a611225277eace2ee0fa74b9fab05fd4406488d41af1331482f38f5a52"},"schema_version":"1.0","source":{"id":"1711.10173","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.10173","created_at":"2026-05-18T00:29:12Z"},{"alias_kind":"arxiv_version","alias_value":"1711.10173v2","created_at":"2026-05-18T00:29:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.10173","created_at":"2026-05-18T00:29:12Z"},{"alias_kind":"pith_short_12","alias_value":"L4FFMGABSAK7","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"L4FFMGABSAK7DHLE","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"L4FFMGAB","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:93cae00e98e3362fb7cf78b10c5b37e78ce772c32111c890d22e0452bce40440","target":"graph","created_at":"2026-05-18T00:29:12Z","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":"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","authors_text":"Masashi Sugiyama, Takayuki Osa","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T08:30:11Z","title":"Hierarchical Policy Search via Return-Weighted Density Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.10173","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:c016543ad6e63534580b27164716e1ef1952174842fcd72555dc013b265532b3","target":"record","created_at":"2026-05-18T00:29:12Z","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":"f654785916bf8e2348328090c346b2f55a5e48a0df8fe7e275fdd6060cd0feb5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-28T08:30:11Z","title_canon_sha256":"12c119a611225277eace2ee0fa74b9fab05fd4406488d41af1331482f38f5a52"},"schema_version":"1.0","source":{"id":"1711.10173","kind":"arxiv","version":2}},"canonical_sha256":"5f0a5618019015f19d64e66bb995b06496f2fe7b76df43ec50c7530396dd7adb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f0a5618019015f19d64e66bb995b06496f2fe7b76df43ec50c7530396dd7adb","first_computed_at":"2026-05-18T00:29:12.712853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:12.712853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hMf2E7W+Y3qIgloA7MY2kFppzAB3tAc6i1R/vZof0DcnDSMFcCeHjm6PvaUodyrdHQi0Ko+sTbYQpR2yIoYvDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:12.713486Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.10173","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c016543ad6e63534580b27164716e1ef1952174842fcd72555dc013b265532b3","sha256:93cae00e98e3362fb7cf78b10c5b37e78ce772c32111c890d22e0452bce40440"],"state_sha256":"af8e60c729ac432fb74b2d16afe41cf82d20815dddc0c6346da90cc6c107a7b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E3xf2wcGnlMp/STS5SbV4UJu6VwQrPmfIpkbrTjyNJHmOh+pr7aWk7oPAXHCqvntIWnNBMDouf1qHtFRuMTcAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:48:41.696012Z","bundle_sha256":"204d4853765d58db13bf376c1d768bd05cd2821b7fafdc17fd30f628ab0ab123"}}