{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NLDP5CEBW7XDTAZVUH563LFZFX","short_pith_number":"pith:NLDP5CEB","schema_version":"1.0","canonical_sha256":"6ac6fe8881b7ee398335a1fbedacb92dd5d90f9c83e59d4e2fe38edcd9726a16","source":{"kind":"arxiv","id":"2606.22145","version":1},"attestation_state":"computed","paper":{"title":"Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Hien Tran, Nikki Xu","submitted_at":"2026-06-20T16:54:36Z","abstract_excerpt":"Reinforcement learning (RL) is a powerful and convenient tool to modernize controller design. In this work, we study the zero-shot transfer of RL-based control policies from simulation to hardware for cart-pole swing-up and stabilization. The two policies are trained independently, and the handoff is implemented in Simulink via switching logic. We apply a first-order action smoothing filter to prevent hardware damage from high-frequency oscillatory actuation. Pairing this bandwidth-aware filtering with sensitivity-guided domain randomization (DR) and a simple linear curriculum learning (CL) sc"},"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":"2606.22145","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-20T16:54:36Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"bff43a001440ab492ad394030d626b8c1f391c7a689ce0cddb18138942df22c8","abstract_canon_sha256":"a33ffa94a1b5daf9798bceb7568360a654265259fc3a7fa525bbcb406c2cebb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:29.554144Z","signature_b64":"keYHpMjCGoIpIAtjPk1q0sWAChFNFXrPzKjRuEzlee+7/NboTyC1EIpkKzUNAfKDDM41a+B638qC9YQSU5GhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ac6fe8881b7ee398335a1fbedacb92dd5d90f9c83e59d4e2fe38edcd9726a16","last_reissued_at":"2026-06-23T02:13:29.553731Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:29.553731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-shot Transfer of Reinforcement Learning Control Policies for the Swing-Up and Stabilization of a Cart-Pole System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Hien Tran, Nikki Xu","submitted_at":"2026-06-20T16:54:36Z","abstract_excerpt":"Reinforcement learning (RL) is a powerful and convenient tool to modernize controller design. In this work, we study the zero-shot transfer of RL-based control policies from simulation to hardware for cart-pole swing-up and stabilization. The two policies are trained independently, and the handoff is implemented in Simulink via switching logic. We apply a first-order action smoothing filter to prevent hardware damage from high-frequency oscillatory actuation. Pairing this bandwidth-aware filtering with sensitivity-guided domain randomization (DR) and a simple linear curriculum learning (CL) sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22145","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/2606.22145/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":"2606.22145","created_at":"2026-06-23T02:13:29.553793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22145v1","created_at":"2026-06-23T02:13:29.553793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22145","created_at":"2026-06-23T02:13:29.553793+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLDP5CEBW7XD","created_at":"2026-06-23T02:13:29.553793+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLDP5CEBW7XDTAZV","created_at":"2026-06-23T02:13:29.553793+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLDP5CEB","created_at":"2026-06-23T02:13:29.553793+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/NLDP5CEBW7XDTAZVUH563LFZFX","json":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX.json","graph_json":"https://pith.science/api/pith-number/NLDP5CEBW7XDTAZVUH563LFZFX/graph.json","events_json":"https://pith.science/api/pith-number/NLDP5CEBW7XDTAZVUH563LFZFX/events.json","paper":"https://pith.science/paper/NLDP5CEB"},"agent_actions":{"view_html":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX","download_json":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX.json","view_paper":"https://pith.science/paper/NLDP5CEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22145&json=true","fetch_graph":"https://pith.science/api/pith-number/NLDP5CEBW7XDTAZVUH563LFZFX/graph.json","fetch_events":"https://pith.science/api/pith-number/NLDP5CEBW7XDTAZVUH563LFZFX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX/action/storage_attestation","attest_author":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX/action/author_attestation","sign_citation":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX/action/citation_signature","submit_replication":"https://pith.science/pith/NLDP5CEBW7XDTAZVUH563LFZFX/action/replication_record"}},"created_at":"2026-06-23T02:13:29.553793+00:00","updated_at":"2026-06-23T02:13:29.553793+00:00"}