{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:S6LRI6J57BHC2LQ67GVFR6RHAH","short_pith_number":"pith:S6LRI6J5","schema_version":"1.0","canonical_sha256":"979714793df84e2d2e1ef9aa58fa2701de3eed114bf5588b5dacced56f0cdaca","source":{"kind":"arxiv","id":"1704.03073","version":1},"attestation_state":"computed","paper":{"title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Gabriel Barth-Maron, Ivaylo Popov, Martin Riedmiller, Matej Vecerik, Nicolas Heess, Roland Hafner, Thomas Lampe, Timothy Lillicrap, Tom Erez, Yuval Tassa","submitted_at":"2017-04-10T22:29:50Z","abstract_excerpt":"Deep learning and reinforcement learning methods have recently been used to solve a variety of problems in continuous control domains. An obvious application of these techniques is dexterous manipulation tasks in robotics which are difficult to solve using traditional control theory or hand-engineered approaches. One example of such a task is to grasp an object and precisely stack it on another. Solving this difficult and practically relevant problem in the real world is an important long-term goal for the field of robotics. Here we take a step towards this goal by examining the problem in sim"},"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":"1704.03073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-10T22:29:50Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"104afe72565a9e1630b6b9a2a76997427dd74fcd094bd4a0d0112ab439373fc8","abstract_canon_sha256":"1ae6d0f643a3cdb4efed9313ca65d157c47267cd2cc875d8120737bcc15b5c14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:33.739294Z","signature_b64":"1vDhian5D6xzjppkCz186fFHUA6kF0GwAoq2583FRgmnR4MRtyiEwtDyHRltcQRPG+ut9jZUHzMmIpQ2pAhSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"979714793df84e2d2e1ef9aa58fa2701de3eed114bf5588b5dacced56f0cdaca","last_reissued_at":"2026-05-18T00:46:33.738536Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:33.738536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-efficient Deep Reinforcement Learning for Dexterous Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Gabriel Barth-Maron, Ivaylo Popov, Martin Riedmiller, Matej Vecerik, Nicolas Heess, Roland Hafner, Thomas Lampe, Timothy Lillicrap, Tom Erez, Yuval Tassa","submitted_at":"2017-04-10T22:29:50Z","abstract_excerpt":"Deep learning and reinforcement learning methods have recently been used to solve a variety of problems in continuous control domains. An obvious application of these techniques is dexterous manipulation tasks in robotics which are difficult to solve using traditional control theory or hand-engineered approaches. One example of such a task is to grasp an object and precisely stack it on another. Solving this difficult and practically relevant problem in the real world is an important long-term goal for the field of robotics. Here we take a step towards this goal by examining the problem in sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03073","kind":"arxiv","version":1},"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":"1704.03073","created_at":"2026-05-18T00:46:33.738655+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.03073v1","created_at":"2026-05-18T00:46:33.738655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03073","created_at":"2026-05-18T00:46:33.738655+00:00"},{"alias_kind":"pith_short_12","alias_value":"S6LRI6J57BHC","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"S6LRI6J57BHC2LQ6","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"S6LRI6J5","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2310.02635","citing_title":"Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2503.11926","citing_title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2506.01665","citing_title":"Leveraging Analytic Gradients in Provably Safe Reinforcement Learning","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13925","citing_title":"Towards Robotic Dexterous Hand Intelligence: A Survey","ref_index":82,"is_internal_anchor":true},{"citing_arxiv_id":"1801.00690","citing_title":"DeepMind Control Suite","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S6LRI6J57BHC2LQ67GVFR6RHAH","json":"https://pith.science/pith/S6LRI6J57BHC2LQ67GVFR6RHAH.json","graph_json":"https://pith.science/api/pith-number/S6LRI6J57BHC2LQ67GVFR6RHAH/graph.json","events_json":"https://pith.science/api/pith-number/S6LRI6J57BHC2LQ67GVFR6RHAH/events.json","paper":"https://pith.science/paper/S6LRI6J5"},"agent_actions":{"view_html":"https://pith.science/pith/S6LRI6J57BHC2LQ67GVFR6RHAH","download_json":"https://pith.science/pith/S6LRI6J57BHC2LQ67GVFR6RHAH.json","view_paper":"https://pith.science/paper/S6LRI6J5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.03073&json=true","fetch_graph":"https://pith.science/api/pith-number/S6LRI6J57BHC2LQ67GVFR6RHAH/graph.json","fetch_events":"https://pith.science/api/pith-number/S6LRI6J57BHC2LQ67GVFR6RHAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S6LRI6J57BHC2LQ67GVFR6RHAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S6LRI6J57BHC2LQ67GVFR6RHAH/action/storage_attestation","attest_author":"https://pith.science/pith/S6LRI6J57BHC2LQ67GVFR6RHAH/action/author_attestation","sign_citation":"https://pith.science/pith/S6LRI6J57BHC2LQ67GVFR6RHAH/action/citation_signature","submit_replication":"https://pith.science/pith/S6LRI6J57BHC2LQ67GVFR6RHAH/action/replication_record"}},"created_at":"2026-05-18T00:46:33.738655+00:00","updated_at":"2026-05-18T00:46:33.738655+00:00"}