{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2OOQ6AYDVOU4P77W2JLUSWXPVI","short_pith_number":"pith:2OOQ6AYD","schema_version":"1.0","canonical_sha256":"d39d0f0303aba9c7fff6d257495aefaa0b364f3c03a9e67ce0545d210a016507","source":{"kind":"arxiv","id":"2002.10621","version":1},"attestation_state":"computed","paper":{"title":"Model-Based Reinforcement Learning for Physical Systems Without Velocity and Acceleration Measurements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SP","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberto Dalla Libera, Bill Yerazunis, Daniel Nikovski, Devesh K. Jha, Diego Romeres","submitted_at":"2020-02-25T01:58:34Z","abstract_excerpt":"In this paper, we propose a derivative-free model learning framework for Reinforcement Learning (RL) algorithms based on Gaussian Process Regression (GPR). In many mechanical systems, only positions can be measured by the sensing instruments. Then, instead of representing the system state as suggested by the physics with a collection of positions, velocities, and accelerations, we define the state as the set of past position measurements. However, the equation of motions derived by physical first principles cannot be directly applied in this framework, being functions of velocities and acceler"},"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":"2002.10621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-25T01:58:34Z","cross_cats_sorted":["cs.RO","cs.SY","eess.SP","eess.SY","stat.ML"],"title_canon_sha256":"1782161f3ed17e36c440f9f0df31d6475d13478a728d4730bc5a473eebc34f0b","abstract_canon_sha256":"5a9e6e3d32193fc8fadefdaa6ad09645b7fca01f22425f5a02547248324b5c2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:23.664854Z","signature_b64":"iwcR3BFG9OoEbkxJCDfCDPlGeiomHODFTl59+9xEktpNse/pKrX9H4Y9SZoi5+H9ZFhGQUg+kG36bJi4nJ3pDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d39d0f0303aba9c7fff6d257495aefaa0b364f3c03a9e67ce0545d210a016507","last_reissued_at":"2026-07-05T00:43:23.664440Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:23.664440Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Based Reinforcement Learning for Physical Systems Without Velocity and Acceleration Measurements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SP","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberto Dalla Libera, Bill Yerazunis, Daniel Nikovski, Devesh K. Jha, Diego Romeres","submitted_at":"2020-02-25T01:58:34Z","abstract_excerpt":"In this paper, we propose a derivative-free model learning framework for Reinforcement Learning (RL) algorithms based on Gaussian Process Regression (GPR). In many mechanical systems, only positions can be measured by the sensing instruments. Then, instead of representing the system state as suggested by the physics with a collection of positions, velocities, and accelerations, we define the state as the set of past position measurements. However, the equation of motions derived by physical first principles cannot be directly applied in this framework, being functions of velocities and acceler"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.10621","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/2002.10621/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":"2002.10621","created_at":"2026-07-05T00:43:23.664504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.10621v1","created_at":"2026-07-05T00:43:23.664504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.10621","created_at":"2026-07-05T00:43:23.664504+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OOQ6AYDVOU4","created_at":"2026-07-05T00:43:23.664504+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OOQ6AYDVOU4P77W","created_at":"2026-07-05T00:43:23.664504+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OOQ6AYD","created_at":"2026-07-05T00:43:23.664504+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/2OOQ6AYDVOU4P77W2JLUSWXPVI","json":"https://pith.science/pith/2OOQ6AYDVOU4P77W2JLUSWXPVI.json","graph_json":"https://pith.science/api/pith-number/2OOQ6AYDVOU4P77W2JLUSWXPVI/graph.json","events_json":"https://pith.science/api/pith-number/2OOQ6AYDVOU4P77W2JLUSWXPVI/events.json","paper":"https://pith.science/paper/2OOQ6AYD"},"agent_actions":{"view_html":"https://pith.science/pith/2OOQ6AYDVOU4P77W2JLUSWXPVI","download_json":"https://pith.science/pith/2OOQ6AYDVOU4P77W2JLUSWXPVI.json","view_paper":"https://pith.science/paper/2OOQ6AYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.10621&json=true","fetch_graph":"https://pith.science/api/pith-number/2OOQ6AYDVOU4P77W2JLUSWXPVI/graph.json","fetch_events":"https://pith.science/api/pith-number/2OOQ6AYDVOU4P77W2JLUSWXPVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OOQ6AYDVOU4P77W2JLUSWXPVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OOQ6AYDVOU4P77W2JLUSWXPVI/action/storage_attestation","attest_author":"https://pith.science/pith/2OOQ6AYDVOU4P77W2JLUSWXPVI/action/author_attestation","sign_citation":"https://pith.science/pith/2OOQ6AYDVOU4P77W2JLUSWXPVI/action/citation_signature","submit_replication":"https://pith.science/pith/2OOQ6AYDVOU4P77W2JLUSWXPVI/action/replication_record"}},"created_at":"2026-07-05T00:43:23.664504+00:00","updated_at":"2026-07-05T00:43:23.664504+00:00"}