{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MCENT4SLQW425Q4WS2H7QZTG6J","short_pith_number":"pith:MCENT4SL","schema_version":"1.0","canonical_sha256":"6088d9f24b85b9aec396968ff86666f2495a3ce24e51b3239755e4690d96a745","source":{"kind":"arxiv","id":"2103.07732","version":1},"attestation_state":"computed","paper":{"title":"Error-Aware Policy Learning: Zero-Shot Generalization in Partially Observable Dynamic Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"C. Karen Liu, Sehoon Ha, Visak Kumar","submitted_at":"2021-03-13T15:36:44Z","abstract_excerpt":"Simulation provides a safe and efficient way to generate useful data for learning complex robotic tasks. However, matching simulation and real-world dynamics can be quite challenging, especially for systems that have a large number of unobserved or unmeasurable parameters, which may lie in the robot dynamics itself or in the environment with which the robot interacts. We introduce a novel approach to tackle such a sim-to-real problem by developing policies capable of adapting to new environments, in a zero-shot manner. Key to our approach is an error-aware policy (EAP) that is explicitly made "},"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":"2103.07732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-03-13T15:36:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a9d3fd86503592dccac79617c1c425b31be574d47252001635680e25313537c0","abstract_canon_sha256":"a7e299658990d5136be4cf4bc23bf7b0c11eab0b6fe3c4080b236986d4b8911a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:44.387812Z","signature_b64":"tTX5OjZIE+N8AJ3a8l3Tq8+Qhcr48xLftGWXjPl1HaBuAsp3N+dod1Jxoy4WIFd28FDJ7fYrAhkjIHkav5P/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6088d9f24b85b9aec396968ff86666f2495a3ce24e51b3239755e4690d96a745","last_reissued_at":"2026-07-05T02:22:44.387468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:44.387468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Error-Aware Policy Learning: Zero-Shot Generalization in Partially Observable Dynamic Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"C. Karen Liu, Sehoon Ha, Visak Kumar","submitted_at":"2021-03-13T15:36:44Z","abstract_excerpt":"Simulation provides a safe and efficient way to generate useful data for learning complex robotic tasks. However, matching simulation and real-world dynamics can be quite challenging, especially for systems that have a large number of unobserved or unmeasurable parameters, which may lie in the robot dynamics itself or in the environment with which the robot interacts. We introduce a novel approach to tackle such a sim-to-real problem by developing policies capable of adapting to new environments, in a zero-shot manner. Key to our approach is an error-aware policy (EAP) that is explicitly made "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.07732","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/2103.07732/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":"2103.07732","created_at":"2026-07-05T02:22:44.387522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.07732v1","created_at":"2026-07-05T02:22:44.387522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.07732","created_at":"2026-07-05T02:22:44.387522+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCENT4SLQW42","created_at":"2026-07-05T02:22:44.387522+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCENT4SLQW425Q4W","created_at":"2026-07-05T02:22:44.387522+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCENT4SL","created_at":"2026-07-05T02:22:44.387522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28476","citing_title":"FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCENT4SLQW425Q4WS2H7QZTG6J","json":"https://pith.science/pith/MCENT4SLQW425Q4WS2H7QZTG6J.json","graph_json":"https://pith.science/api/pith-number/MCENT4SLQW425Q4WS2H7QZTG6J/graph.json","events_json":"https://pith.science/api/pith-number/MCENT4SLQW425Q4WS2H7QZTG6J/events.json","paper":"https://pith.science/paper/MCENT4SL"},"agent_actions":{"view_html":"https://pith.science/pith/MCENT4SLQW425Q4WS2H7QZTG6J","download_json":"https://pith.science/pith/MCENT4SLQW425Q4WS2H7QZTG6J.json","view_paper":"https://pith.science/paper/MCENT4SL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.07732&json=true","fetch_graph":"https://pith.science/api/pith-number/MCENT4SLQW425Q4WS2H7QZTG6J/graph.json","fetch_events":"https://pith.science/api/pith-number/MCENT4SLQW425Q4WS2H7QZTG6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCENT4SLQW425Q4WS2H7QZTG6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCENT4SLQW425Q4WS2H7QZTG6J/action/storage_attestation","attest_author":"https://pith.science/pith/MCENT4SLQW425Q4WS2H7QZTG6J/action/author_attestation","sign_citation":"https://pith.science/pith/MCENT4SLQW425Q4WS2H7QZTG6J/action/citation_signature","submit_replication":"https://pith.science/pith/MCENT4SLQW425Q4WS2H7QZTG6J/action/replication_record"}},"created_at":"2026-07-05T02:22:44.387522+00:00","updated_at":"2026-07-05T02:22:44.387522+00:00"}