{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:TBAW3QYMJY5Z3QHEP34CIP3DWZ","short_pith_number":"pith:TBAW3QYM","schema_version":"1.0","canonical_sha256":"98416dc30c4e3b9dc0e47ef8243f63b646124bd7468199f50cbb77296deb1c52","source":{"kind":"arxiv","id":"1612.07139","version":4},"attestation_state":"computed","paper":{"title":"A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY"],"primary_cat":"cs.RO","authors_text":"Jingwei Zhang, Joschka Boedecker, Lei Tai, Ming Liu, Wolfram Burgard","submitted_at":"2016-12-21T14:31:47Z","abstract_excerpt":"Deep learning techniques have been widely applied, achieving state-of-the-art results in various fields of study. This survey focuses on deep learning solutions that target learning control policies for robotics applications. We carry out our discussions on the two main paradigms for learning control with deep networks: deep reinforcement learning and imitation learning. For deep reinforcement learning (DRL), we begin from traditional reinforcement learning algorithms, showing how they are extended to the deep context and effective mechanisms that could be added on top of the DRL algorithms. 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":"1612.07139","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-12-21T14:31:47Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY"],"title_canon_sha256":"57036fc2f1d7637c100e2c043f597e37274a49da7a554afde47a44b884546f8e","abstract_canon_sha256":"410acf87c1dee0bc96856030021f0d93076c9aa9877085cc4c49805edfe78e58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:04.342173Z","signature_b64":"+YteTeyMxk1hyOT7/akdnUziLhjufBT14uU/rJ17lPQEPUaz+LQsPHEF8ewglmUm7wH8OBCdy31P4R7+DNqdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98416dc30c4e3b9dc0e47ef8243f63b646124bd7468199f50cbb77296deb1c52","last_reissued_at":"2026-05-18T00:19:04.341516Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:04.341516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY"],"primary_cat":"cs.RO","authors_text":"Jingwei Zhang, Joschka Boedecker, Lei Tai, Ming Liu, Wolfram Burgard","submitted_at":"2016-12-21T14:31:47Z","abstract_excerpt":"Deep learning techniques have been widely applied, achieving state-of-the-art results in various fields of study. This survey focuses on deep learning solutions that target learning control policies for robotics applications. We carry out our discussions on the two main paradigms for learning control with deep networks: deep reinforcement learning and imitation learning. For deep reinforcement learning (DRL), we begin from traditional reinforcement learning algorithms, showing how they are extended to the deep context and effective mechanisms that could be added on top of the DRL algorithms. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.07139","kind":"arxiv","version":4},"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":"1612.07139","created_at":"2026-05-18T00:19:04.341612+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.07139v4","created_at":"2026-05-18T00:19:04.341612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.07139","created_at":"2026-05-18T00:19:04.341612+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBAW3QYMJY5Z","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBAW3QYMJY5Z3QHE","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBAW3QYM","created_at":"2026-05-18T12:30:44.179134+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/TBAW3QYMJY5Z3QHEP34CIP3DWZ","json":"https://pith.science/pith/TBAW3QYMJY5Z3QHEP34CIP3DWZ.json","graph_json":"https://pith.science/api/pith-number/TBAW3QYMJY5Z3QHEP34CIP3DWZ/graph.json","events_json":"https://pith.science/api/pith-number/TBAW3QYMJY5Z3QHEP34CIP3DWZ/events.json","paper":"https://pith.science/paper/TBAW3QYM"},"agent_actions":{"view_html":"https://pith.science/pith/TBAW3QYMJY5Z3QHEP34CIP3DWZ","download_json":"https://pith.science/pith/TBAW3QYMJY5Z3QHEP34CIP3DWZ.json","view_paper":"https://pith.science/paper/TBAW3QYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.07139&json=true","fetch_graph":"https://pith.science/api/pith-number/TBAW3QYMJY5Z3QHEP34CIP3DWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/TBAW3QYMJY5Z3QHEP34CIP3DWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBAW3QYMJY5Z3QHEP34CIP3DWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBAW3QYMJY5Z3QHEP34CIP3DWZ/action/storage_attestation","attest_author":"https://pith.science/pith/TBAW3QYMJY5Z3QHEP34CIP3DWZ/action/author_attestation","sign_citation":"https://pith.science/pith/TBAW3QYMJY5Z3QHEP34CIP3DWZ/action/citation_signature","submit_replication":"https://pith.science/pith/TBAW3QYMJY5Z3QHEP34CIP3DWZ/action/replication_record"}},"created_at":"2026-05-18T00:19:04.341612+00:00","updated_at":"2026-05-18T00:19:04.341612+00:00"}