{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BP2EJJC3DGT5NMPYIL7W22ZHZK","short_pith_number":"pith:BP2EJJC3","schema_version":"1.0","canonical_sha256":"0bf444a45b19a7d6b1f842ff6d6b27ca902b4391db53631ecc7f718852fedbe9","source":{"kind":"arxiv","id":"1702.02453","version":3},"attestation_state":"computed","paper":{"title":"Preparing for the Unknown: Learning a Universal Policy with Online System Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY"],"primary_cat":"cs.LG","authors_text":"C. Karen Liu, Greg Turk, Jie Tan, Wenhao Yu","submitted_at":"2017-02-08T14:53:45Z","abstract_excerpt":"We present a new method of learning control policies that successfully operate under unknown dynamic models. We create such policies by leveraging a large number of training examples that are generated using a physical simulator. Our system is made of two components: a Universal Policy (UP) and a function for Online System Identification (OSI). We describe our control policy as universal because it is trained over a wide array of dynamic models. These variations in the dynamic model may include differences in mass and inertia of the robots' components, variable friction coefficients, or unknow"},"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":"1702.02453","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-08T14:53:45Z","cross_cats_sorted":["cs.RO","cs.SY"],"title_canon_sha256":"ff513509ef223a48a1e4b024e3d30eb407e2a2e47eb79fa79a102bd64a5728e7","abstract_canon_sha256":"55da1d23200e05182c7236e027f3b1c9d84510c4a31a8391e034cb5c899788b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:33.479710Z","signature_b64":"3EltWVeDd2XWZp4YV1BSi3f+9XyFqizGt1/Q+XOl/KuVURT4nrWRMdNscjZF8TGWahQD4IX3y4/140tzZ6dPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bf444a45b19a7d6b1f842ff6d6b27ca902b4391db53631ecc7f718852fedbe9","last_reissued_at":"2026-05-18T00:44:33.479261Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:33.479261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preparing for the Unknown: Learning a Universal Policy with Online System Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY"],"primary_cat":"cs.LG","authors_text":"C. Karen Liu, Greg Turk, Jie Tan, Wenhao Yu","submitted_at":"2017-02-08T14:53:45Z","abstract_excerpt":"We present a new method of learning control policies that successfully operate under unknown dynamic models. We create such policies by leveraging a large number of training examples that are generated using a physical simulator. Our system is made of two components: a Universal Policy (UP) and a function for Online System Identification (OSI). We describe our control policy as universal because it is trained over a wide array of dynamic models. These variations in the dynamic model may include differences in mass and inertia of the robots' components, variable friction coefficients, or unknow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02453","kind":"arxiv","version":3},"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":"1702.02453","created_at":"2026-05-18T00:44:33.479354+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.02453v3","created_at":"2026-05-18T00:44:33.479354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02453","created_at":"2026-05-18T00:44:33.479354+00:00"},{"alias_kind":"pith_short_12","alias_value":"BP2EJJC3DGT5","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BP2EJJC3DGT5NMPY","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BP2EJJC3","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1907.11740","citing_title":"Environment Probing Interaction Policies","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09183","citing_title":"Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"1910.11215","citing_title":"RoboNet: Large-Scale Multi-Robot Learning","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02348","citing_title":"Contextual Intelligence The Next Leap for Reinforcement Learning","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2603.23964","citing_title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","ref_index":174,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09183","citing_title":"Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09789","citing_title":"Zero-Shot Sim-to-Real Robot Learning: A Dexterous Manipulation Study on Reactive Catching","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BP2EJJC3DGT5NMPYIL7W22ZHZK","json":"https://pith.science/pith/BP2EJJC3DGT5NMPYIL7W22ZHZK.json","graph_json":"https://pith.science/api/pith-number/BP2EJJC3DGT5NMPYIL7W22ZHZK/graph.json","events_json":"https://pith.science/api/pith-number/BP2EJJC3DGT5NMPYIL7W22ZHZK/events.json","paper":"https://pith.science/paper/BP2EJJC3"},"agent_actions":{"view_html":"https://pith.science/pith/BP2EJJC3DGT5NMPYIL7W22ZHZK","download_json":"https://pith.science/pith/BP2EJJC3DGT5NMPYIL7W22ZHZK.json","view_paper":"https://pith.science/paper/BP2EJJC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.02453&json=true","fetch_graph":"https://pith.science/api/pith-number/BP2EJJC3DGT5NMPYIL7W22ZHZK/graph.json","fetch_events":"https://pith.science/api/pith-number/BP2EJJC3DGT5NMPYIL7W22ZHZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BP2EJJC3DGT5NMPYIL7W22ZHZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BP2EJJC3DGT5NMPYIL7W22ZHZK/action/storage_attestation","attest_author":"https://pith.science/pith/BP2EJJC3DGT5NMPYIL7W22ZHZK/action/author_attestation","sign_citation":"https://pith.science/pith/BP2EJJC3DGT5NMPYIL7W22ZHZK/action/citation_signature","submit_replication":"https://pith.science/pith/BP2EJJC3DGT5NMPYIL7W22ZHZK/action/replication_record"}},"created_at":"2026-05-18T00:44:33.479354+00:00","updated_at":"2026-05-18T00:44:33.479354+00:00"}