{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7MR74TPLEPHHSVQIBLHXHZL56A","short_pith_number":"pith:7MR74TPL","canonical_record":{"source":{"id":"1901.01365","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-05T04:43:05Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4df7b9843c8a1b5c70f5338dfbc3a1516843feac3413b4111087c25a6f1353eb","abstract_canon_sha256":"d2a59d0b786990b3d68cb84c3b531c9549f242d112943bf89728e779cb1e154d"},"schema_version":"1.0"},"canonical_sha256":"fb23fe4deb23ce7956080acf73e57df03bcc78025047922abb2315288ab091d7","source":{"kind":"arxiv","id":"1901.01365","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.01365","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1901.01365v2","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01365","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"7MR74TPLEPHH","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7MR74TPLEPHHSVQI","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7MR74TPL","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7MR74TPLEPHHSVQIBLHXHZL56A","target":"record","payload":{"canonical_record":{"source":{"id":"1901.01365","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-05T04:43:05Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4df7b9843c8a1b5c70f5338dfbc3a1516843feac3413b4111087c25a6f1353eb","abstract_canon_sha256":"d2a59d0b786990b3d68cb84c3b531c9549f242d112943bf89728e779cb1e154d"},"schema_version":"1.0"},"canonical_sha256":"fb23fe4deb23ce7956080acf73e57df03bcc78025047922abb2315288ab091d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:52.134570Z","signature_b64":"uC2ZhPtMEezq4QdHwS8BLf+rI7i7EoWYUKFMdfRlDzOLkgHNuXJJ4yCT6VpwZxshZaBnGWF6RVvJK0aycYJfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb23fe4deb23ce7956080acf73e57df03bcc78025047922abb2315288ab091d7","last_reissued_at":"2026-05-17T23:51:52.133910Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:52.133910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.01365","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":"2026-05-17T23:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9CJl2Og1kOmpN7w8gsl7Dqzrb5Li8s6wOK1j0hUWlu8mwVpDsGf6MI38cwccp3alz+FiBFoXjiBwpLx8Uf+XCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:34:51.606691Z"},"content_sha256":"9cb8b37b6d7c5ff7ae4d7f3e35c11eea9e923fdce996f6ccd4d645d8d8135d8c","schema_version":"1.0","event_id":"sha256:9cb8b37b6d7c5ff7ae4d7f3e35c11eea9e923fdce996f6ccd4d645d8d8135d8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7MR74TPLEPHHSVQIBLHXHZL56A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Masashi Sugiyama, Takayuki Osa, Voot Tangkaratt","submitted_at":"2019-01-05T04:43:05Z","abstract_excerpt":"Real-world tasks are often highly structured. Hierarchical reinforcement learning (HRL) has attracted research interest as an approach for leveraging the hierarchical structure of a given task in reinforcement learning (RL). However, identifying the hierarchical policy structure that enhances the performance of RL is not a trivial task. In this paper, we propose an HRL method that learns a latent variable of a hierarchical policy using mutual information maximization. Our approach can be interpreted as a way to learn a discrete and latent representation of the state-action space. To learn opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01365","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":"2026-05-17T23:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8bn8gCRBG75HYi+3L38AOfvg9C/VhczGdDpDLpQ3jv5xogdUmI5BN2kmipD7u1xF2zRPXonacn8gMTYiDWVQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:34:51.607044Z"},"content_sha256":"fba1ba2dbc9937f1c6c0cd48bddfb6911ea11b1e2154c95451e906c2711efff2","schema_version":"1.0","event_id":"sha256:fba1ba2dbc9937f1c6c0cd48bddfb6911ea11b1e2154c95451e906c2711efff2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A/bundle.json","state_url":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7MR74TPLEPHHSVQIBLHXHZL56A/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":"2026-05-26T11:34:51Z","links":{"resolver":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A","bundle":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A/bundle.json","state":"https://pith.science/pith/7MR74TPLEPHHSVQIBLHXHZL56A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7MR74TPLEPHHSVQIBLHXHZL56A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7MR74TPLEPHHSVQIBLHXHZL56A","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":"d2a59d0b786990b3d68cb84c3b531c9549f242d112943bf89728e779cb1e154d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-05T04:43:05Z","title_canon_sha256":"4df7b9843c8a1b5c70f5338dfbc3a1516843feac3413b4111087c25a6f1353eb"},"schema_version":"1.0","source":{"id":"1901.01365","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.01365","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"1901.01365v2","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01365","created_at":"2026-05-17T23:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"7MR74TPLEPHH","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7MR74TPLEPHHSVQI","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7MR74TPL","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:fba1ba2dbc9937f1c6c0cd48bddfb6911ea11b1e2154c95451e906c2711efff2","target":"graph","created_at":"2026-05-17T23:51:52Z","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":"Real-world tasks are often highly structured. Hierarchical reinforcement learning (HRL) has attracted research interest as an approach for leveraging the hierarchical structure of a given task in reinforcement learning (RL). However, identifying the hierarchical policy structure that enhances the performance of RL is not a trivial task. In this paper, we propose an HRL method that learns a latent variable of a hierarchical policy using mutual information maximization. Our approach can be interpreted as a way to learn a discrete and latent representation of the state-action space. To learn opti","authors_text":"Masashi Sugiyama, Takayuki Osa, Voot Tangkaratt","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-05T04:43:05Z","title":"Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01365","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":"sha256:9cb8b37b6d7c5ff7ae4d7f3e35c11eea9e923fdce996f6ccd4d645d8d8135d8c","target":"record","created_at":"2026-05-17T23:51:52Z","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":"d2a59d0b786990b3d68cb84c3b531c9549f242d112943bf89728e779cb1e154d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-05T04:43:05Z","title_canon_sha256":"4df7b9843c8a1b5c70f5338dfbc3a1516843feac3413b4111087c25a6f1353eb"},"schema_version":"1.0","source":{"id":"1901.01365","kind":"arxiv","version":2}},"canonical_sha256":"fb23fe4deb23ce7956080acf73e57df03bcc78025047922abb2315288ab091d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb23fe4deb23ce7956080acf73e57df03bcc78025047922abb2315288ab091d7","first_computed_at":"2026-05-17T23:51:52.133910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:52.133910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uC2ZhPtMEezq4QdHwS8BLf+rI7i7EoWYUKFMdfRlDzOLkgHNuXJJ4yCT6VpwZxshZaBnGWF6RVvJK0aycYJfBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:52.134570Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.01365","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cb8b37b6d7c5ff7ae4d7f3e35c11eea9e923fdce996f6ccd4d645d8d8135d8c","sha256:fba1ba2dbc9937f1c6c0cd48bddfb6911ea11b1e2154c95451e906c2711efff2"],"state_sha256":"b03e9de362dbd61001469ab86ee0c212677663c551873a45cccadfb0be0ab9b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7FArAawM+dnU+wdbFedXSvrsvyUgfXeuPoEgbl1QSBiaRKZGGJoqXoQy3K6RLgbvzLhG2AWa6AAAqIvZEoWjDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:34:51.609789Z","bundle_sha256":"827ad93ffbe216559fecc7880cc87760fd220a71477dee4eb78bb091d8b39a40"}}