{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:G7AW7MWNXIGQKD26UMX3KQ6AB6","short_pith_number":"pith:G7AW7MWN","schema_version":"1.0","canonical_sha256":"37c16fb2cdba0d050f5ea32fb543c00fb15c807b0fa0ae9602831d0688af0559","source":{"kind":"arxiv","id":"1803.04996","version":2},"attestation_state":"computed","paper":{"title":"Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Fadri Furrer, Juan Nieto, Michel Breyer, Roland Siegwart, Tonci Novkovic","submitted_at":"2018-03-13T18:20:13Z","abstract_excerpt":"Enabling autonomous robots to interact in unstructured environments with dynamic objects requires manipulation capabilities that can deal with clutter, changes, and objects' variability. This paper presents a comparison of different reinforcement learning-based approaches for object picking with a robotic manipulator. We learn closed-loop policies mapping depth camera inputs to motion commands and compare different approaches to keep the problem tractable, including reward shaping, curriculum learning and using a policy pre-trained on a task with a reduced action set to warm-start the full pro"},"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":"1803.04996","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-03-13T18:20:13Z","cross_cats_sorted":[],"title_canon_sha256":"09dcba012a4e9943db8b672280f4eba343656fe3e14f537528ffc4e645d293b9","abstract_canon_sha256":"1ef8c3ee3bab3bb29f90febaf726defc8091d51a47de709caa65663163e8e787"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:03.563168Z","signature_b64":"ZioEe18LdUDwBhGSt/3cVO433p3dtNgN08PtpAVFd4KRZZGstfK6BniEXaXZLMnBhbz8WK+fE+GCe8oBTizbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37c16fb2cdba0d050f5ea32fb543c00fb15c807b0fa0ae9602831d0688af0559","last_reissued_at":"2026-05-17T23:55:03.562747Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:03.562747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparing Task Simplifications to Learn Closed-Loop Object Picking Using Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Fadri Furrer, Juan Nieto, Michel Breyer, Roland Siegwart, Tonci Novkovic","submitted_at":"2018-03-13T18:20:13Z","abstract_excerpt":"Enabling autonomous robots to interact in unstructured environments with dynamic objects requires manipulation capabilities that can deal with clutter, changes, and objects' variability. This paper presents a comparison of different reinforcement learning-based approaches for object picking with a robotic manipulator. We learn closed-loop policies mapping depth camera inputs to motion commands and compare different approaches to keep the problem tractable, including reward shaping, curriculum learning and using a policy pre-trained on a task with a reduced action set to warm-start the full pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.04996","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":"1803.04996","created_at":"2026-05-17T23:55:03.562824+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.04996v2","created_at":"2026-05-17T23:55:03.562824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.04996","created_at":"2026-05-17T23:55:03.562824+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7AW7MWNXIGQ","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7AW7MWNXIGQKD26","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7AW7MWN","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.08787","citing_title":"One Interface, Many Robots: Unified Real-Time Low-Level Motion Planning for Collaborative Arms","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G7AW7MWNXIGQKD26UMX3KQ6AB6","json":"https://pith.science/pith/G7AW7MWNXIGQKD26UMX3KQ6AB6.json","graph_json":"https://pith.science/api/pith-number/G7AW7MWNXIGQKD26UMX3KQ6AB6/graph.json","events_json":"https://pith.science/api/pith-number/G7AW7MWNXIGQKD26UMX3KQ6AB6/events.json","paper":"https://pith.science/paper/G7AW7MWN"},"agent_actions":{"view_html":"https://pith.science/pith/G7AW7MWNXIGQKD26UMX3KQ6AB6","download_json":"https://pith.science/pith/G7AW7MWNXIGQKD26UMX3KQ6AB6.json","view_paper":"https://pith.science/paper/G7AW7MWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.04996&json=true","fetch_graph":"https://pith.science/api/pith-number/G7AW7MWNXIGQKD26UMX3KQ6AB6/graph.json","fetch_events":"https://pith.science/api/pith-number/G7AW7MWNXIGQKD26UMX3KQ6AB6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7AW7MWNXIGQKD26UMX3KQ6AB6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7AW7MWNXIGQKD26UMX3KQ6AB6/action/storage_attestation","attest_author":"https://pith.science/pith/G7AW7MWNXIGQKD26UMX3KQ6AB6/action/author_attestation","sign_citation":"https://pith.science/pith/G7AW7MWNXIGQKD26UMX3KQ6AB6/action/citation_signature","submit_replication":"https://pith.science/pith/G7AW7MWNXIGQKD26UMX3KQ6AB6/action/replication_record"}},"created_at":"2026-05-17T23:55:03.562824+00:00","updated_at":"2026-05-17T23:55:03.562824+00:00"}