{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6BACT2L2FNLGRG2WMS745GT22X","short_pith_number":"pith:6BACT2L2","schema_version":"1.0","canonical_sha256":"f04029e97a2b56689b5664bfce9a7ad5c91736631d09de9283a0c8f91af632e0","source":{"kind":"arxiv","id":"2010.03799","version":1},"attestation_state":"computed","paper":{"title":"Learning the Linear Quadratic Regulator from Nonlinear Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Alexander Rakhlin, Dipendra Misra, Dylan J. Foster, John Langford, Max Simchowitz, Wen Sun, Zakaria Mhammedi","submitted_at":"2020-10-08T07:02:47Z","abstract_excerpt":"We introduce a new problem setting for continuous control called the LQR with Rich Observations, or RichLQR. In our setting, the environment is summarized by a low-dimensional continuous latent state with linear dynamics and quadratic costs, but the agent operates on high-dimensional, nonlinear observations such as images from a camera. To enable sample-efficient learning, we assume that the learner has access to a class of decoder functions (e.g., neural networks) that is flexible enough to capture the mapping from observations to latent states. We introduce a new algorithm, RichID, which lea"},"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":"2010.03799","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-08T07:02:47Z","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"50d5d951a47c4ab375265d969d8d1a2f87683a4d27cb56f38be2d3aa92d89450","abstract_canon_sha256":"e34503acc0952fcf130e29feabf810128c0b352e5d45c6ec7b1a12536c3d7503"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:23.731060Z","signature_b64":"jGArao3VAs94Zwug5+NUhxNCUj+0FRZ/cIRMDaEs2Do8t60gyhNbafnCmeD59NCxgf8yfmsDtroxXzpG+jHQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f04029e97a2b56689b5664bfce9a7ad5c91736631d09de9283a0c8f91af632e0","last_reissued_at":"2026-07-05T01:41:23.730677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:23.730677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning the Linear Quadratic Regulator from Nonlinear Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Alexander Rakhlin, Dipendra Misra, Dylan J. Foster, John Langford, Max Simchowitz, Wen Sun, Zakaria Mhammedi","submitted_at":"2020-10-08T07:02:47Z","abstract_excerpt":"We introduce a new problem setting for continuous control called the LQR with Rich Observations, or RichLQR. In our setting, the environment is summarized by a low-dimensional continuous latent state with linear dynamics and quadratic costs, but the agent operates on high-dimensional, nonlinear observations such as images from a camera. To enable sample-efficient learning, we assume that the learner has access to a class of decoder functions (e.g., neural networks) that is flexible enough to capture the mapping from observations to latent states. We introduce a new algorithm, RichID, which lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03799","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/2010.03799/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":"2010.03799","created_at":"2026-07-05T01:41:23.730741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.03799v1","created_at":"2026-07-05T01:41:23.730741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03799","created_at":"2026-07-05T01:41:23.730741+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BACT2L2FNLG","created_at":"2026-07-05T01:41:23.730741+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BACT2L2FNLGRG2W","created_at":"2026-07-05T01:41:23.730741+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BACT2L2","created_at":"2026-07-05T01:41:23.730741+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/6BACT2L2FNLGRG2WMS745GT22X","json":"https://pith.science/pith/6BACT2L2FNLGRG2WMS745GT22X.json","graph_json":"https://pith.science/api/pith-number/6BACT2L2FNLGRG2WMS745GT22X/graph.json","events_json":"https://pith.science/api/pith-number/6BACT2L2FNLGRG2WMS745GT22X/events.json","paper":"https://pith.science/paper/6BACT2L2"},"agent_actions":{"view_html":"https://pith.science/pith/6BACT2L2FNLGRG2WMS745GT22X","download_json":"https://pith.science/pith/6BACT2L2FNLGRG2WMS745GT22X.json","view_paper":"https://pith.science/paper/6BACT2L2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.03799&json=true","fetch_graph":"https://pith.science/api/pith-number/6BACT2L2FNLGRG2WMS745GT22X/graph.json","fetch_events":"https://pith.science/api/pith-number/6BACT2L2FNLGRG2WMS745GT22X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BACT2L2FNLGRG2WMS745GT22X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BACT2L2FNLGRG2WMS745GT22X/action/storage_attestation","attest_author":"https://pith.science/pith/6BACT2L2FNLGRG2WMS745GT22X/action/author_attestation","sign_citation":"https://pith.science/pith/6BACT2L2FNLGRG2WMS745GT22X/action/citation_signature","submit_replication":"https://pith.science/pith/6BACT2L2FNLGRG2WMS745GT22X/action/replication_record"}},"created_at":"2026-07-05T01:41:23.730741+00:00","updated_at":"2026-07-05T01:41:23.730741+00:00"}