{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2SAZCTW6HRMVOLN5HDLO6SFENT","short_pith_number":"pith:2SAZCTW6","schema_version":"1.0","canonical_sha256":"d481914ede3c59572dbd38d6ef48a46cd09fc7023735b0d0d365388d8011ef49","source":{"kind":"arxiv","id":"1910.13439","version":2},"attestation_state":"computed","paper":{"title":"Learning to Manipulate Deformable Objects without Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Lerrel Pinto, Pieter Abbeel, Thanard Kurutach, Wilson Yan, Yilin Wu","submitted_at":"2019-10-29T17:56:56Z","abstract_excerpt":"In this paper we tackle the problem of deformable object manipulation through model-free visual reinforcement learning (RL). In order to circumvent the sample inefficiency of RL, we propose two key ideas that accelerate learning. First, we propose an iterative pick-place action space that encodes the conditional relationship between picking and placing on deformable objects. The explicit structural encoding enables faster learning under complex object dynamics. Second, instead of jointly learning both the pick and the place locations, we only explicitly learn the placing policy conditioned on "},"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":"1910.13439","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-10-29T17:56:56Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"004c0fb8a78a6c25d744a6972d50a60614d2dcb08e2ec413cdc113e9e998380a","abstract_canon_sha256":"de44cff89a093670234403ce8c119a3760eb2764523cf808e8f97f6244dcac92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:45:13.115660Z","signature_b64":"FHhsn8DKo3OpZtd5k+aDWq6Ndr6uKMUbnTFn+myla8uPSnNVIRldy2zThJ1EE8zvxrVeZ+z8wE6YEOib53KAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d481914ede3c59572dbd38d6ef48a46cd09fc7023735b0d0d365388d8011ef49","last_reissued_at":"2026-07-05T00:45:13.115212Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:45:13.115212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Manipulate Deformable Objects without Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Lerrel Pinto, Pieter Abbeel, Thanard Kurutach, Wilson Yan, Yilin Wu","submitted_at":"2019-10-29T17:56:56Z","abstract_excerpt":"In this paper we tackle the problem of deformable object manipulation through model-free visual reinforcement learning (RL). In order to circumvent the sample inefficiency of RL, we propose two key ideas that accelerate learning. First, we propose an iterative pick-place action space that encodes the conditional relationship between picking and placing on deformable objects. The explicit structural encoding enables faster learning under complex object dynamics. Second, instead of jointly learning both the pick and the place locations, we only explicitly learn the placing policy conditioned on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13439","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.13439/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1910.13439","created_at":"2026-07-05T00:45:13.115269+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.13439v2","created_at":"2026-07-05T00:45:13.115269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13439","created_at":"2026-07-05T00:45:13.115269+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SAZCTW6HRMV","created_at":"2026-07-05T00:45:13.115269+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SAZCTW6HRMVOLN5","created_at":"2026-07-05T00:45:13.115269+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SAZCTW6","created_at":"2026-07-05T00:45:13.115269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.15953","citing_title":"ViTacFormer: Learning Cross-Modal Representation for Visuo-Tactile Dexterous Manipulation","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2411.04983","citing_title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2SAZCTW6HRMVOLN5HDLO6SFENT","json":"https://pith.science/pith/2SAZCTW6HRMVOLN5HDLO6SFENT.json","graph_json":"https://pith.science/api/pith-number/2SAZCTW6HRMVOLN5HDLO6SFENT/graph.json","events_json":"https://pith.science/api/pith-number/2SAZCTW6HRMVOLN5HDLO6SFENT/events.json","paper":"https://pith.science/paper/2SAZCTW6"},"agent_actions":{"view_html":"https://pith.science/pith/2SAZCTW6HRMVOLN5HDLO6SFENT","download_json":"https://pith.science/pith/2SAZCTW6HRMVOLN5HDLO6SFENT.json","view_paper":"https://pith.science/paper/2SAZCTW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.13439&json=true","fetch_graph":"https://pith.science/api/pith-number/2SAZCTW6HRMVOLN5HDLO6SFENT/graph.json","fetch_events":"https://pith.science/api/pith-number/2SAZCTW6HRMVOLN5HDLO6SFENT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SAZCTW6HRMVOLN5HDLO6SFENT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SAZCTW6HRMVOLN5HDLO6SFENT/action/storage_attestation","attest_author":"https://pith.science/pith/2SAZCTW6HRMVOLN5HDLO6SFENT/action/author_attestation","sign_citation":"https://pith.science/pith/2SAZCTW6HRMVOLN5HDLO6SFENT/action/citation_signature","submit_replication":"https://pith.science/pith/2SAZCTW6HRMVOLN5HDLO6SFENT/action/replication_record"}},"created_at":"2026-07-05T00:45:13.115269+00:00","updated_at":"2026-07-05T00:45:13.115269+00:00"}