{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YCQSX5QYKOMTWHGEJ2ZL6DOC4L","short_pith_number":"pith:YCQSX5QY","schema_version":"1.0","canonical_sha256":"c0a12bf61853993b1cc44eb2bf0dc2e2e76634662bcfdcbf9907344b79b84917","source":{"kind":"arxiv","id":"1802.10264","version":2},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Deirdre Quillen, Eric Jang, Julian Ibarz, Ofir Nachum, Sergey Levine","submitted_at":"2018-02-28T05:11:38Z","abstract_excerpt":"In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping. Model-free deep reinforcement learning (RL) has been successfully applied to a range of challenging environments, but the proliferation of algorithms makes it difficult to discern which particular approach would be best suited for a rich, diverse task like grasping. To answer this question, we propose a simulated benchmark for robotic grasping that emphasizes off-policy learning and generalization to unseen objects. Off-policy learning enables utilization of grasping data over a wide variety of "},"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":"1802.10264","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-02-28T05:11:38Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"a79abbe7b3bb5942f12d2c4c455e94d83637323ca356877ad8f3c86302c1558d","abstract_canon_sha256":"9228bbaa973cb8be2b8cfca71b51bb3a54bd71ad79cc6ae8203c9c280d29c316"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:50.690555Z","signature_b64":"MDfsU2cjgfXp2MuFUhpFY9bpbI6Q+1YUyqOt2Hg+fCKSuE61dUvmWK8KJJUT/Jd3u3M8eVT7OzHAhk+iFIYBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0a12bf61853993b1cc44eb2bf0dc2e2e76634662bcfdcbf9907344b79b84917","last_reissued_at":"2026-05-18T00:19:50.689788Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:50.689788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.RO","authors_text":"Chelsea Finn, Deirdre Quillen, Eric Jang, Julian Ibarz, Ofir Nachum, Sergey Levine","submitted_at":"2018-02-28T05:11:38Z","abstract_excerpt":"In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping. Model-free deep reinforcement learning (RL) has been successfully applied to a range of challenging environments, but the proliferation of algorithms makes it difficult to discern which particular approach would be best suited for a rich, diverse task like grasping. To answer this question, we propose a simulated benchmark for robotic grasping that emphasizes off-policy learning and generalization to unseen objects. Off-policy learning enables utilization of grasping data over a wide variety of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10264","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":"1802.10264","created_at":"2026-05-18T00:19:50.689933+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.10264v2","created_at":"2026-05-18T00:19:50.689933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10264","created_at":"2026-05-18T00:19:50.689933+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCQSX5QYKOMT","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCQSX5QYKOMTWHGE","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCQSX5QY","created_at":"2026-05-18T12:33:04.347982+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/YCQSX5QYKOMTWHGEJ2ZL6DOC4L","json":"https://pith.science/pith/YCQSX5QYKOMTWHGEJ2ZL6DOC4L.json","graph_json":"https://pith.science/api/pith-number/YCQSX5QYKOMTWHGEJ2ZL6DOC4L/graph.json","events_json":"https://pith.science/api/pith-number/YCQSX5QYKOMTWHGEJ2ZL6DOC4L/events.json","paper":"https://pith.science/paper/YCQSX5QY"},"agent_actions":{"view_html":"https://pith.science/pith/YCQSX5QYKOMTWHGEJ2ZL6DOC4L","download_json":"https://pith.science/pith/YCQSX5QYKOMTWHGEJ2ZL6DOC4L.json","view_paper":"https://pith.science/paper/YCQSX5QY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.10264&json=true","fetch_graph":"https://pith.science/api/pith-number/YCQSX5QYKOMTWHGEJ2ZL6DOC4L/graph.json","fetch_events":"https://pith.science/api/pith-number/YCQSX5QYKOMTWHGEJ2ZL6DOC4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCQSX5QYKOMTWHGEJ2ZL6DOC4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCQSX5QYKOMTWHGEJ2ZL6DOC4L/action/storage_attestation","attest_author":"https://pith.science/pith/YCQSX5QYKOMTWHGEJ2ZL6DOC4L/action/author_attestation","sign_citation":"https://pith.science/pith/YCQSX5QYKOMTWHGEJ2ZL6DOC4L/action/citation_signature","submit_replication":"https://pith.science/pith/YCQSX5QYKOMTWHGEJ2ZL6DOC4L/action/replication_record"}},"created_at":"2026-05-18T00:19:50.689933+00:00","updated_at":"2026-05-18T00:19:50.689933+00:00"}