{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:C5K2XAC7YX2RTAHOQCNG52QIPI","short_pith_number":"pith:C5K2XAC7","schema_version":"1.0","canonical_sha256":"1755ab805fc5f51980ee809a6eea087a1cd06fd26b00f69f38179d70c225ce68","source":{"kind":"arxiv","id":"1904.06786","version":2},"attestation_state":"computed","paper":{"title":"Curious iLQR: Resolving Uncertainty in Model-based RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Akshara Rai, Franziska Meier, Ludovic Righetti, Sarah Bechtle, Yixin Lin","submitted_at":"2019-04-15T00:02:27Z","abstract_excerpt":"Curiosity as a means to explore during reinforcement learning problems has recently become very popular. However, very little progress has been made in utilizing curiosity for learning control. In this work, we propose a model-based reinforcement learning (MBRL) framework that combines Bayesian modeling of the system dynamics with curious iLQR, an iterative LQR approach that considers model uncertainty. During trajectory optimization the curious iLQR attempts to minimize both the task-dependent cost and the uncertainty in the dynamics model. We demonstrate the approach on reaching tasks with 7"},"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":"1904.06786","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-04-15T00:02:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"52d1b8fff26029146318aaa256ddcb7473593621673e353e1c830bf116ce64b0","abstract_canon_sha256":"053e81c4fca7880664d11a85f2cf40fea585a277765a5020f9e400e95e6fdf21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:14.454066Z","signature_b64":"RvJcTcqFRw7orLzg6moteAirqjFkb+LW4LMHv33S2SIrm+J75LqcCURmB5REara0EyuQGJcCD0Fh34MXDGfjDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1755ab805fc5f51980ee809a6eea087a1cd06fd26b00f69f38179d70c225ce68","last_reissued_at":"2026-07-05T00:10:14.453552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:14.453552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curious iLQR: Resolving Uncertainty in Model-based RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Akshara Rai, Franziska Meier, Ludovic Righetti, Sarah Bechtle, Yixin Lin","submitted_at":"2019-04-15T00:02:27Z","abstract_excerpt":"Curiosity as a means to explore during reinforcement learning problems has recently become very popular. However, very little progress has been made in utilizing curiosity for learning control. In this work, we propose a model-based reinforcement learning (MBRL) framework that combines Bayesian modeling of the system dynamics with curious iLQR, an iterative LQR approach that considers model uncertainty. During trajectory optimization the curious iLQR attempts to minimize both the task-dependent cost and the uncertainty in the dynamics model. We demonstrate the approach on reaching tasks with 7"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06786","kind":"arxiv","version":2},"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/1904.06786/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":"1904.06786","created_at":"2026-07-05T00:10:14.453622+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.06786v2","created_at":"2026-07-05T00:10:14.453622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06786","created_at":"2026-07-05T00:10:14.453622+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5K2XAC7YX2R","created_at":"2026-07-05T00:10:14.453622+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5K2XAC7YX2RTAHO","created_at":"2026-07-05T00:10:14.453622+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5K2XAC7","created_at":"2026-07-05T00:10:14.453622+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/C5K2XAC7YX2RTAHOQCNG52QIPI","json":"https://pith.science/pith/C5K2XAC7YX2RTAHOQCNG52QIPI.json","graph_json":"https://pith.science/api/pith-number/C5K2XAC7YX2RTAHOQCNG52QIPI/graph.json","events_json":"https://pith.science/api/pith-number/C5K2XAC7YX2RTAHOQCNG52QIPI/events.json","paper":"https://pith.science/paper/C5K2XAC7"},"agent_actions":{"view_html":"https://pith.science/pith/C5K2XAC7YX2RTAHOQCNG52QIPI","download_json":"https://pith.science/pith/C5K2XAC7YX2RTAHOQCNG52QIPI.json","view_paper":"https://pith.science/paper/C5K2XAC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.06786&json=true","fetch_graph":"https://pith.science/api/pith-number/C5K2XAC7YX2RTAHOQCNG52QIPI/graph.json","fetch_events":"https://pith.science/api/pith-number/C5K2XAC7YX2RTAHOQCNG52QIPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5K2XAC7YX2RTAHOQCNG52QIPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5K2XAC7YX2RTAHOQCNG52QIPI/action/storage_attestation","attest_author":"https://pith.science/pith/C5K2XAC7YX2RTAHOQCNG52QIPI/action/author_attestation","sign_citation":"https://pith.science/pith/C5K2XAC7YX2RTAHOQCNG52QIPI/action/citation_signature","submit_replication":"https://pith.science/pith/C5K2XAC7YX2RTAHOQCNG52QIPI/action/replication_record"}},"created_at":"2026-07-05T00:10:14.453622+00:00","updated_at":"2026-07-05T00:10:14.453622+00:00"}