{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LDSQYDCY76MRLDYWND2CYGJGAY","short_pith_number":"pith:LDSQYDCY","schema_version":"1.0","canonical_sha256":"58e50c0c58ff99158f1668f42c19260625c3546483c102ff83e5bb7547085693","source":{"kind":"arxiv","id":"1703.00472","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Pivoting Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Christian Smith, Danica Kragic, Rika Antonova, Silvia Cruciani","submitted_at":"2017-03-01T19:25:55Z","abstract_excerpt":"In this work we propose an approach to learn a robust policy for solving the pivoting task. Recently, several model-free continuous control algorithms were shown to learn successful policies without prior knowledge of the dynamics of the task. However, obtaining successful policies required thousands to millions of training episodes, limiting the applicability of these approaches to real hardware. We developed a training procedure that allows us to use a simple custom simulator to learn policies robust to the mismatch of simulation vs robot. In our experiments, we demonstrate that the policy l"},"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":"1703.00472","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-01T19:25:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3e99b7011d9fd44e748c801e9dc3a2873718390bb8d4f0a34627dcf3676bf4dd","abstract_canon_sha256":"4014bbd7f9c4f0841ac81a60ac609596d713bb3fba544b17c60d7826362932f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:41.586698Z","signature_b64":"rIVviRtsvfxAzd/IHTtnAWCWsh1VoPMpO4DJuQQSb7+c94gJszpZlyf0q3Z5xVDn6eOalUlT9dns186/6SewDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58e50c0c58ff99158f1668f42c19260625c3546483c102ff83e5bb7547085693","last_reissued_at":"2026-05-18T00:49:41.586226Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:41.586226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Pivoting Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Christian Smith, Danica Kragic, Rika Antonova, Silvia Cruciani","submitted_at":"2017-03-01T19:25:55Z","abstract_excerpt":"In this work we propose an approach to learn a robust policy for solving the pivoting task. Recently, several model-free continuous control algorithms were shown to learn successful policies without prior knowledge of the dynamics of the task. However, obtaining successful policies required thousands to millions of training episodes, limiting the applicability of these approaches to real hardware. We developed a training procedure that allows us to use a simple custom simulator to learn policies robust to the mismatch of simulation vs robot. In our experiments, we demonstrate that the policy l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00472","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":"1703.00472","created_at":"2026-05-18T00:49:41.586297+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00472v1","created_at":"2026-05-18T00:49:41.586297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00472","created_at":"2026-05-18T00:49:41.586297+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDSQYDCY76MR","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDSQYDCY76MRLDYW","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDSQYDCY","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDSQYDCY76MRLDYWND2CYGJGAY","json":"https://pith.science/pith/LDSQYDCY76MRLDYWND2CYGJGAY.json","graph_json":"https://pith.science/api/pith-number/LDSQYDCY76MRLDYWND2CYGJGAY/graph.json","events_json":"https://pith.science/api/pith-number/LDSQYDCY76MRLDYWND2CYGJGAY/events.json","paper":"https://pith.science/paper/LDSQYDCY"},"agent_actions":{"view_html":"https://pith.science/pith/LDSQYDCY76MRLDYWND2CYGJGAY","download_json":"https://pith.science/pith/LDSQYDCY76MRLDYWND2CYGJGAY.json","view_paper":"https://pith.science/paper/LDSQYDCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00472&json=true","fetch_graph":"https://pith.science/api/pith-number/LDSQYDCY76MRLDYWND2CYGJGAY/graph.json","fetch_events":"https://pith.science/api/pith-number/LDSQYDCY76MRLDYWND2CYGJGAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDSQYDCY76MRLDYWND2CYGJGAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDSQYDCY76MRLDYWND2CYGJGAY/action/storage_attestation","attest_author":"https://pith.science/pith/LDSQYDCY76MRLDYWND2CYGJGAY/action/author_attestation","sign_citation":"https://pith.science/pith/LDSQYDCY76MRLDYWND2CYGJGAY/action/citation_signature","submit_replication":"https://pith.science/pith/LDSQYDCY76MRLDYWND2CYGJGAY/action/replication_record"}},"created_at":"2026-05-18T00:49:41.586297+00:00","updated_at":"2026-05-18T00:49:41.586297+00:00"}