{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QFEI5DX5FCOSZGETGESZV25WWU","short_pith_number":"pith:QFEI5DX5","schema_version":"1.0","canonical_sha256":"81488e8efd289d2c989331259aebb6b522379a9ba322a7779df1118648a99917","source":{"kind":"arxiv","id":"2005.11810","version":1},"attestation_state":"computed","paper":{"title":"Learning visual servo policies via planner cloning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Kate Saenko, Robert Platt, Ulrich Viereck","submitted_at":"2020-05-24T17:56:57Z","abstract_excerpt":"Learning control policies for visual servoing in novel environments is an important problem. However, standard model-free policy learning methods are slow. This paper explores planner cloning: using behavior cloning to learn policies that mimic the behavior of a full-state motion planner in simulation. We propose Penalized Q Cloning (PQC), a new behavior cloning algorithm. We show that it outperforms several baselines and ablations on some challenging problems involving visual servoing in novel environments while avoiding obstacles. Finally, we demonstrate that these policies can be transferre"},"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":"2005.11810","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-05-24T17:56:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"181b0b37bb237d131141efb4f6ad5d9f4eddfd58c58107d6d10ccfb647a751c8","abstract_canon_sha256":"8d3fad7f03ab71288d963864304ab4319988e862e9bcb9327cb55aead17e7134"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:28.460135Z","signature_b64":"3oIaXUxRgRi8oaYo2I3vYjHN9QP0vUEKUBYp2UVmRI5Ou/5FlOvBOj+PZiLAZTq2pvQylC2lbUkMvcdHQfZ8AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81488e8efd289d2c989331259aebb6b522379a9ba322a7779df1118648a99917","last_reissued_at":"2026-07-05T01:05:28.459636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:28.459636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning visual servo policies via planner cloning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Kate Saenko, Robert Platt, Ulrich Viereck","submitted_at":"2020-05-24T17:56:57Z","abstract_excerpt":"Learning control policies for visual servoing in novel environments is an important problem. However, standard model-free policy learning methods are slow. This paper explores planner cloning: using behavior cloning to learn policies that mimic the behavior of a full-state motion planner in simulation. We propose Penalized Q Cloning (PQC), a new behavior cloning algorithm. We show that it outperforms several baselines and ablations on some challenging problems involving visual servoing in novel environments while avoiding obstacles. Finally, we demonstrate that these policies can be transferre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.11810","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.11810/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":"2005.11810","created_at":"2026-07-05T01:05:28.459693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.11810v1","created_at":"2026-07-05T01:05:28.459693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.11810","created_at":"2026-07-05T01:05:28.459693+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFEI5DX5FCOS","created_at":"2026-07-05T01:05:28.459693+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFEI5DX5FCOSZGET","created_at":"2026-07-05T01:05:28.459693+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFEI5DX5","created_at":"2026-07-05T01:05:28.459693+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/QFEI5DX5FCOSZGETGESZV25WWU","json":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU.json","graph_json":"https://pith.science/api/pith-number/QFEI5DX5FCOSZGETGESZV25WWU/graph.json","events_json":"https://pith.science/api/pith-number/QFEI5DX5FCOSZGETGESZV25WWU/events.json","paper":"https://pith.science/paper/QFEI5DX5"},"agent_actions":{"view_html":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU","download_json":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU.json","view_paper":"https://pith.science/paper/QFEI5DX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.11810&json=true","fetch_graph":"https://pith.science/api/pith-number/QFEI5DX5FCOSZGETGESZV25WWU/graph.json","fetch_events":"https://pith.science/api/pith-number/QFEI5DX5FCOSZGETGESZV25WWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU/action/storage_attestation","attest_author":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU/action/author_attestation","sign_citation":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU/action/citation_signature","submit_replication":"https://pith.science/pith/QFEI5DX5FCOSZGETGESZV25WWU/action/replication_record"}},"created_at":"2026-07-05T01:05:28.459693+00:00","updated_at":"2026-07-05T01:05:28.459693+00:00"}