{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ODXWLQUGPOGNC3ACYAHSXJRHOF","short_pith_number":"pith:ODXWLQUG","schema_version":"1.0","canonical_sha256":"70ef65c2867b8cd16c02c00f2ba627716034055ff543f2c65ca3efa6fdab809b","source":{"kind":"arxiv","id":"1803.05752","version":1},"attestation_state":"computed","paper":{"title":"Rearrangement with Nonprehensile Manipulation Using Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Danica Kragic, Johannes A. Stork, Kaiyu Hang, Michael Y. Wang, Weihao Yuan","submitted_at":"2018-03-15T14:00:24Z","abstract_excerpt":"Rearranging objects on a tabletop surface by means of nonprehensile manipulation is a task which requires skillful interaction with the physical world. Usually, this is achieved by precisely modeling physical properties of the objects, robot, and the environment for explicit planning. In contrast, as explicitly modeling the physical environment is not always feasible and involves various uncertainties, we learn a nonprehensile rearrangement strategy with deep reinforcement learning based on only visual feedback. For this, we model the task with rewards and train a deep Q-network. Our potential"},"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":"1803.05752","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-15T14:00:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8ecc28d22cc83b1edde69a42c930dfe82543c2187abfad27fd06d4bd59529ecb","abstract_canon_sha256":"5c7257a8b431c9593c91bd82dab08009a8f3441ac3b8a472d9aa799ee95a6dcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:19.429756Z","signature_b64":"wCfKS/Ldv/3OeXBHmky/kqHYh9b5pHL1XMLSVYnQBWrRgSdDvmClta0td3oeNFt6tkm8dsGHhDDm+kdJLR/0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70ef65c2867b8cd16c02c00f2ba627716034055ff543f2c65ca3efa6fdab809b","last_reissued_at":"2026-05-18T00:05:19.429188Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:19.429188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rearrangement with Nonprehensile Manipulation Using Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Danica Kragic, Johannes A. Stork, Kaiyu Hang, Michael Y. Wang, Weihao Yuan","submitted_at":"2018-03-15T14:00:24Z","abstract_excerpt":"Rearranging objects on a tabletop surface by means of nonprehensile manipulation is a task which requires skillful interaction with the physical world. Usually, this is achieved by precisely modeling physical properties of the objects, robot, and the environment for explicit planning. In contrast, as explicitly modeling the physical environment is not always feasible and involves various uncertainties, we learn a nonprehensile rearrangement strategy with deep reinforcement learning based on only visual feedback. For this, we model the task with rewards and train a deep Q-network. Our potential"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05752","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":"1803.05752","created_at":"2026-05-18T00:05:19.429272+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.05752v1","created_at":"2026-05-18T00:05:19.429272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05752","created_at":"2026-05-18T00:05:19.429272+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODXWLQUGPOGN","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODXWLQUGPOGNC3AC","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODXWLQUG","created_at":"2026-05-18T12:32:43.782077+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/ODXWLQUGPOGNC3ACYAHSXJRHOF","json":"https://pith.science/pith/ODXWLQUGPOGNC3ACYAHSXJRHOF.json","graph_json":"https://pith.science/api/pith-number/ODXWLQUGPOGNC3ACYAHSXJRHOF/graph.json","events_json":"https://pith.science/api/pith-number/ODXWLQUGPOGNC3ACYAHSXJRHOF/events.json","paper":"https://pith.science/paper/ODXWLQUG"},"agent_actions":{"view_html":"https://pith.science/pith/ODXWLQUGPOGNC3ACYAHSXJRHOF","download_json":"https://pith.science/pith/ODXWLQUGPOGNC3ACYAHSXJRHOF.json","view_paper":"https://pith.science/paper/ODXWLQUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.05752&json=true","fetch_graph":"https://pith.science/api/pith-number/ODXWLQUGPOGNC3ACYAHSXJRHOF/graph.json","fetch_events":"https://pith.science/api/pith-number/ODXWLQUGPOGNC3ACYAHSXJRHOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODXWLQUGPOGNC3ACYAHSXJRHOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODXWLQUGPOGNC3ACYAHSXJRHOF/action/storage_attestation","attest_author":"https://pith.science/pith/ODXWLQUGPOGNC3ACYAHSXJRHOF/action/author_attestation","sign_citation":"https://pith.science/pith/ODXWLQUGPOGNC3ACYAHSXJRHOF/action/citation_signature","submit_replication":"https://pith.science/pith/ODXWLQUGPOGNC3ACYAHSXJRHOF/action/replication_record"}},"created_at":"2026-05-18T00:05:19.429272+00:00","updated_at":"2026-05-18T00:05:19.429272+00:00"}