{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GDURU7NJWMOBJSGYIMS33OYM24","short_pith_number":"pith:GDURU7NJ","schema_version":"1.0","canonical_sha256":"30e91a7da9b31c14c8d84325bdbb0cd7115a165c3599a741425d1d5255472c97","source":{"kind":"arxiv","id":"1804.02808","version":2},"attestation_state":"computed","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 "},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1804.02808","created_at":"2026-05-18T00:06:40.233526+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.02808v2","created_at":"2026-05-18T00:06:40.233526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02808","created_at":"2026-05-18T00:06:40.233526+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDURU7NJWMOB","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDURU7NJWMOBJSGY","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDURU7NJ","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.10667","citing_title":"Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"1907.00664","citing_title":"Learning World Graphs to Accelerate Hierarchical Reinforcement Learning","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06143","citing_title":"Neural Embedding for Physical Manipulations","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"1805.00909","citing_title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24","json":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24.json","graph_json":"https://pith.science/api/pith-number/GDURU7NJWMOBJSGYIMS33OYM24/graph.json","events_json":"https://pith.science/api/pith-number/GDURU7NJWMOBJSGYIMS33OYM24/events.json","paper":"https://pith.science/paper/GDURU7NJ"},"agent_actions":{"view_html":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24","download_json":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24.json","view_paper":"https://pith.science/paper/GDURU7NJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.02808&json=true","fetch_graph":"https://pith.science/api/pith-number/GDURU7NJWMOBJSGYIMS33OYM24/graph.json","fetch_events":"https://pith.science/api/pith-number/GDURU7NJWMOBJSGYIMS33OYM24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24/action/storage_attestation","attest_author":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24/action/author_attestation","sign_citation":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24/action/citation_signature","submit_replication":"https://pith.science/pith/GDURU7NJWMOBJSGYIMS33OYM24/action/replication_record"}},"created_at":"2026-05-18T00:06:40.233526+00:00","updated_at":"2026-05-18T00:06:40.233526+00:00"}