{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GDURU7NJWMOBJSGYIMS33OYM24","short_pith_number":"pith:GDURU7NJ","canonical_record":{"source":{"id":"1804.02808","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-09T04:00:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3bc6b14dce54f7dfaaf6f293256a09eb84b7d4fc53903e4dc65f4f4cc36f07a7","abstract_canon_sha256":"a7f5aeee46d773c4a2b3ee9dc85c1652ca1e8e664e73b5b3ae992ef45fe42a30"},"schema_version":"1.0"},"canonical_sha256":"30e91a7da9b31c14c8d84325bdbb0cd7115a165c3599a741425d1d5255472c97","source":{"kind":"arxiv","id":"1804.02808","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02808","created_at":"2026-05-18T00:06:40Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02808v2","created_at":"2026-05-18T00:06:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02808","created_at":"2026-05-18T00:06:40Z"},{"alias_kind":"pith_short_12","alias_value":"GDURU7NJWMOB","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GDURU7NJWMOBJSGY","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GDURU7NJ","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GDURU7NJWMOBJSGYIMS33OYM24","target":"record","payload":{"canonical_record":{"source":{"id":"1804.02808","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-09T04:00:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3bc6b14dce54f7dfaaf6f293256a09eb84b7d4fc53903e4dc65f4f4cc36f07a7","abstract_canon_sha256":"a7f5aeee46d773c4a2b3ee9dc85c1652ca1e8e664e73b5b3ae992ef45fe42a30"},"schema_version":"1.0"},"canonical_sha256":"30e91a7da9b31c14c8d84325bdbb0cd7115a165c3599a741425d1d5255472c97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:40.233866Z","signature_b64":"AlWFOdPtqrbkeY3DifjbAGmIVAoY3E7wnX9XK25ZyXTeNDLMbAdDCrayXf4zOPcpvQpYykzxk1EV6N8Dp6z6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30e91a7da9b31c14c8d84325bdbb0cd7115a165c3599a741425d1d5255472c97","last_reissued_at":"2026-05-18T00:06:40.233467Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:40.233467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.02808","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":"2026-05-18T00:06:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iQCa+LfHNH+/zhuxRIlewZoEULUMe1y6+ggdSEA3GLJBeckHrU3OjhZFth/Ti1KGaGl/ereK0xHCrJOMltBaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:52:13.269367Z"},"content_sha256":"0521bee1fda2b0b77fe1b134960190535ba72c127a5c3544418a8f80f7b8ff19","schema_version":"1.0","event_id":"sha256:0521bee1fda2b0b77fe1b134960190535ba72c127a5c3544418a8f80f7b8ff19"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GDURU7NJWMOBJSGYIMS33OYM24","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Space Policies for Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kristian Hartikainen, Pieter Abbeel, Sergey Levine, Tuomas Haarnoja","submitted_at":"2018-04-09T04:00:30Z","abstract_excerpt":"We address the problem of learning hierarchical deep neural network policies for reinforcement learning. In contrast to methods that explicitly restrict or cripple lower layers of a hierarchy to force them to use higher-level modulating signals, each layer in our framework is trained to directly solve the task, but acquires a range of diverse strategies via a maximum entropy reinforcement learning objective. Each layer is also augmented with latent random variables, which are sampled from a prior distribution during the training of that layer. The maximum entropy objective causes these latent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02808","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":"2026-05-18T00:06:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zKJespx04AlA5xCIP03oyDxvUXPPulNQENqAV9FQWMjg1hY340djpooHUFob7g3H/dyjejmrj79z1zv4Y6DbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T16:52:13.269718Z"},"content_sha256":"731084db8cbb49cca5e10bc4b1836320af93ad431c48793fae9e109ffb820db2","schema_version":"1.0","event_id":"sha256:731084db8cbb49cca5e10bc4b1836320af93ad431c48793fae9e109ffb820db2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24/bundle.json","state_url":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDURU7NJWMOBJSGYIMS33OYM24/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":"2026-06-01T16:52:13Z","links":{"resolver":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24","bundle":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24/bundle.json","state":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDURU7NJWMOBJSGYIMS33OYM24/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GDURU7NJWMOBJSGYIMS33OYM24","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":"a7f5aeee46d773c4a2b3ee9dc85c1652ca1e8e664e73b5b3ae992ef45fe42a30","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-09T04:00:30Z","title_canon_sha256":"3bc6b14dce54f7dfaaf6f293256a09eb84b7d4fc53903e4dc65f4f4cc36f07a7"},"schema_version":"1.0","source":{"id":"1804.02808","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02808","created_at":"2026-05-18T00:06:40Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02808v2","created_at":"2026-05-18T00:06:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02808","created_at":"2026-05-18T00:06:40Z"},{"alias_kind":"pith_short_12","alias_value":"GDURU7NJWMOB","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GDURU7NJWMOBJSGY","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GDURU7NJ","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:731084db8cbb49cca5e10bc4b1836320af93ad431c48793fae9e109ffb820db2","target":"graph","created_at":"2026-05-18T00:06:40Z","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":"We address the problem of learning hierarchical deep neural network policies for reinforcement learning. In contrast to methods that explicitly restrict or cripple lower layers of a hierarchy to force them to use higher-level modulating signals, each layer in our framework is trained to directly solve the task, but acquires a range of diverse strategies via a maximum entropy reinforcement learning objective. Each layer is also augmented with latent random variables, which are sampled from a prior distribution during the training of that layer. The maximum entropy objective causes these latent ","authors_text":"Kristian Hartikainen, Pieter Abbeel, Sergey Levine, Tuomas Haarnoja","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-09T04:00:30Z","title":"Latent Space Policies for Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02808","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":"sha256:0521bee1fda2b0b77fe1b134960190535ba72c127a5c3544418a8f80f7b8ff19","target":"record","created_at":"2026-05-18T00:06:40Z","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":"a7f5aeee46d773c4a2b3ee9dc85c1652ca1e8e664e73b5b3ae992ef45fe42a30","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-09T04:00:30Z","title_canon_sha256":"3bc6b14dce54f7dfaaf6f293256a09eb84b7d4fc53903e4dc65f4f4cc36f07a7"},"schema_version":"1.0","source":{"id":"1804.02808","kind":"arxiv","version":2}},"canonical_sha256":"30e91a7da9b31c14c8d84325bdbb0cd7115a165c3599a741425d1d5255472c97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30e91a7da9b31c14c8d84325bdbb0cd7115a165c3599a741425d1d5255472c97","first_computed_at":"2026-05-18T00:06:40.233467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:40.233467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AlWFOdPtqrbkeY3DifjbAGmIVAoY3E7wnX9XK25ZyXTeNDLMbAdDCrayXf4zOPcpvQpYykzxk1EV6N8Dp6z6Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:40.233866Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.02808","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0521bee1fda2b0b77fe1b134960190535ba72c127a5c3544418a8f80f7b8ff19","sha256:731084db8cbb49cca5e10bc4b1836320af93ad431c48793fae9e109ffb820db2"],"state_sha256":"8da22b56cebb247ad083b0bc5640606a814cf23bf1ac5bfbd687996c92ffe5d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3sLg2ChKRziqzVJwZQdCJWbrPdndu8Tk7aU+YMD/728A0hlkY6ghl79EtkUtoMfYE8EL7qa+TJkDn1XTXyoMCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T16:52:13.271727Z","bundle_sha256":"18ea6965fd0c31fd21e06ff07234b272c4e40ee72b08eada13761884e2b2812d"}}