{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KHVJTXHUZ7URGEABOLSMGUADCP","short_pith_number":"pith:KHVJTXHU","schema_version":"1.0","canonical_sha256":"51ea99dcf4cfe913100172e4c3500313d52e5603398ff96320f20266452c0378","source":{"kind":"arxiv","id":"1902.04696","version":1},"attestation_state":"computed","paper":{"title":"Using Approximate Models in Robot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ali Lenjani","submitted_at":"2019-02-13T01:33:27Z","abstract_excerpt":"Trajectory following is one of the complicated control problems when its dynamics are nonlinear, stochastic and include a large number of parameters. The problem has significant difficulties including a large number of trials required for data collection and a massive volume of computations required to find a closed-loop controller for high dimensional and stochastic domains. For solving this type of problem, if we have an appropriate reward function and dynamics model; finding an optimal control policy is possible by using model-based reinforcement learning and optimal control algorithms. How"},"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":"1902.04696","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-02-13T01:33:27Z","cross_cats_sorted":[],"title_canon_sha256":"bcf698a5fa97443093cd75e1ca9047a8f73236b50e7d1b65474dafd2ec6404c1","abstract_canon_sha256":"2730be5a3f912bd1482399c3f41d494a0a0416aa03f952e717b05d95c4deded4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:06.257901Z","signature_b64":"YxGuZ2LDr5N5zZZ9/gVNYR3obwufXWzcJp0CoNlC4gno7aKr11iSdBaBtswW98e+XX8BvVCc+jkpqW5qYC3FBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51ea99dcf4cfe913100172e4c3500313d52e5603398ff96320f20266452c0378","last_reissued_at":"2026-05-17T23:54:06.257473Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:06.257473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Approximate Models in Robot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ali Lenjani","submitted_at":"2019-02-13T01:33:27Z","abstract_excerpt":"Trajectory following is one of the complicated control problems when its dynamics are nonlinear, stochastic and include a large number of parameters. The problem has significant difficulties including a large number of trials required for data collection and a massive volume of computations required to find a closed-loop controller for high dimensional and stochastic domains. For solving this type of problem, if we have an appropriate reward function and dynamics model; finding an optimal control policy is possible by using model-based reinforcement learning and optimal control algorithms. How"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04696","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":""},"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":"1902.04696","created_at":"2026-05-17T23:54:06.257536+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.04696v1","created_at":"2026-05-17T23:54:06.257536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04696","created_at":"2026-05-17T23:54:06.257536+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHVJTXHUZ7UR","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHVJTXHUZ7URGEAB","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHVJTXHU","created_at":"2026-05-18T12:33:21.387695+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/KHVJTXHUZ7URGEABOLSMGUADCP","json":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP.json","graph_json":"https://pith.science/api/pith-number/KHVJTXHUZ7URGEABOLSMGUADCP/graph.json","events_json":"https://pith.science/api/pith-number/KHVJTXHUZ7URGEABOLSMGUADCP/events.json","paper":"https://pith.science/paper/KHVJTXHU"},"agent_actions":{"view_html":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP","download_json":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP.json","view_paper":"https://pith.science/paper/KHVJTXHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.04696&json=true","fetch_graph":"https://pith.science/api/pith-number/KHVJTXHUZ7URGEABOLSMGUADCP/graph.json","fetch_events":"https://pith.science/api/pith-number/KHVJTXHUZ7URGEABOLSMGUADCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP/action/storage_attestation","attest_author":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP/action/author_attestation","sign_citation":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP/action/citation_signature","submit_replication":"https://pith.science/pith/KHVJTXHUZ7URGEABOLSMGUADCP/action/replication_record"}},"created_at":"2026-05-17T23:54:06.257536+00:00","updated_at":"2026-05-17T23:54:06.257536+00:00"}