{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6BACT2L2FNLGRG2WMS745GT22X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e34503acc0952fcf130e29feabf810128c0b352e5d45c6ec7b1a12536c3d7503","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-08T07:02:47Z","title_canon_sha256":"50d5d951a47c4ab375265d969d8d1a2f87683a4d27cb56f38be2d3aa92d89450"},"schema_version":"1.0","source":{"id":"2010.03799","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.03799","created_at":"2026-07-05T01:41:23Z"},{"alias_kind":"arxiv_version","alias_value":"2010.03799v1","created_at":"2026-07-05T01:41:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03799","created_at":"2026-07-05T01:41:23Z"},{"alias_kind":"pith_short_12","alias_value":"6BACT2L2FNLG","created_at":"2026-07-05T01:41:23Z"},{"alias_kind":"pith_short_16","alias_value":"6BACT2L2FNLGRG2W","created_at":"2026-07-05T01:41:23Z"},{"alias_kind":"pith_short_8","alias_value":"6BACT2L2","created_at":"2026-07-05T01:41:23Z"}],"graph_snapshots":[{"event_id":"sha256:ad9bbbf270422790c58c9d30f1154c3dc4d9204fa2027e3279d378ae36348053","target":"graph","created_at":"2026-07-05T01:41:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.03799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Akshay Krishnamurthy, Alexander Rakhlin, Dipendra Misra, Dylan J. Foster, John Langford, Max Simchowitz, Wen Sun, Zakaria Mhammedi","cross_cats":["math.OC","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-08T07:02:47Z","title":"Learning the Linear Quadratic Regulator from Nonlinear Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03799","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f076e47543c35d66c9e765f4d618a490ee4d928be922a6a1f0e14b51a300f0a4","target":"record","created_at":"2026-07-05T01:41:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e34503acc0952fcf130e29feabf810128c0b352e5d45c6ec7b1a12536c3d7503","cross_cats_sorted":["math.OC","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-08T07:02:47Z","title_canon_sha256":"50d5d951a47c4ab375265d969d8d1a2f87683a4d27cb56f38be2d3aa92d89450"},"schema_version":"1.0","source":{"id":"2010.03799","kind":"arxiv","version":1}},"canonical_sha256":"f04029e97a2b56689b5664bfce9a7ad5c91736631d09de9283a0c8f91af632e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f04029e97a2b56689b5664bfce9a7ad5c91736631d09de9283a0c8f91af632e0","first_computed_at":"2026-07-05T01:41:23.730677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:41:23.730677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jGArao3VAs94Zwug5+NUhxNCUj+0FRZ/cIRMDaEs2Do8t60gyhNbafnCmeD59NCxgf8yfmsDtroxXzpG+jHQBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:41:23.731060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.03799","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f076e47543c35d66c9e765f4d618a490ee4d928be922a6a1f0e14b51a300f0a4","sha256:ad9bbbf270422790c58c9d30f1154c3dc4d9204fa2027e3279d378ae36348053"],"state_sha256":"23d5d80db33acc49db3c519abb1584a8b77477a459dfff49df6a31db638b0d61"}