{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AQFDJ76HEQYZILSY47SZ75GL22","short_pith_number":"pith:AQFDJ76H","schema_version":"1.0","canonical_sha256":"040a34ffc72431942e58e7e59ff4cbd68601512b90877ad1a481029cce0c70bb","source":{"kind":"arxiv","id":"2304.05889","version":1},"attestation_state":"computed","paper":{"title":"Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Dylan J. Foster, Zakaria Mhammedi","submitted_at":"2023-04-12T14:51:47Z","abstract_excerpt":"We study the design of sample-efficient algorithms for reinforcement learning in the presence of rich, high-dimensional observations, formalized via the Block MDP problem. Existing algorithms suffer from either 1) computational intractability, 2) strong statistical assumptions that are not necessarily satisfied in practice, or 3) suboptimal sample complexity. We address these issues by providing the first computationally efficient algorithm that attains rate-optimal sample complexity with respect to the desired accuracy level, with minimal statistical assumptions. Our algorithm, MusIK, combine"},"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":"2304.05889","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-12T14:51:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b2ffbad41857508e991f08a9721cc2103dae085b5dbccc42c0270af0d8c499aa","abstract_canon_sha256":"8fd84d0d8f4814168dec78261538e2946edaf6da798933f218e1b6c1c9dbfbcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:25.337871Z","signature_b64":"XaXY4vwEBLT2QyM6oxHmTQ22+RID1BZ00VWZKAwzilx+PKAsGVoBYPpu7LrIGYXcsFoskbWrAg0fWfgA8bZBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"040a34ffc72431942e58e7e59ff4cbd68601512b90877ad1a481029cce0c70bb","last_reissued_at":"2026-07-05T06:00:25.337416Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:25.337416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Dylan J. Foster, Zakaria Mhammedi","submitted_at":"2023-04-12T14:51:47Z","abstract_excerpt":"We study the design of sample-efficient algorithms for reinforcement learning in the presence of rich, high-dimensional observations, formalized via the Block MDP problem. Existing algorithms suffer from either 1) computational intractability, 2) strong statistical assumptions that are not necessarily satisfied in practice, or 3) suboptimal sample complexity. We address these issues by providing the first computationally efficient algorithm that attains rate-optimal sample complexity with respect to the desired accuracy level, with minimal statistical assumptions. Our algorithm, MusIK, combine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05889","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/2304.05889/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":"2304.05889","created_at":"2026-07-05T06:00:25.337480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.05889v1","created_at":"2026-07-05T06:00:25.337480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05889","created_at":"2026-07-05T06:00:25.337480+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQFDJ76HEQYZ","created_at":"2026-07-05T06:00:25.337480+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQFDJ76HEQYZILSY","created_at":"2026-07-05T06:00:25.337480+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQFDJ76H","created_at":"2026-07-05T06:00:25.337480+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/AQFDJ76HEQYZILSY47SZ75GL22","json":"https://pith.science/pith/AQFDJ76HEQYZILSY47SZ75GL22.json","graph_json":"https://pith.science/api/pith-number/AQFDJ76HEQYZILSY47SZ75GL22/graph.json","events_json":"https://pith.science/api/pith-number/AQFDJ76HEQYZILSY47SZ75GL22/events.json","paper":"https://pith.science/paper/AQFDJ76H"},"agent_actions":{"view_html":"https://pith.science/pith/AQFDJ76HEQYZILSY47SZ75GL22","download_json":"https://pith.science/pith/AQFDJ76HEQYZILSY47SZ75GL22.json","view_paper":"https://pith.science/paper/AQFDJ76H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.05889&json=true","fetch_graph":"https://pith.science/api/pith-number/AQFDJ76HEQYZILSY47SZ75GL22/graph.json","fetch_events":"https://pith.science/api/pith-number/AQFDJ76HEQYZILSY47SZ75GL22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQFDJ76HEQYZILSY47SZ75GL22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQFDJ76HEQYZILSY47SZ75GL22/action/storage_attestation","attest_author":"https://pith.science/pith/AQFDJ76HEQYZILSY47SZ75GL22/action/author_attestation","sign_citation":"https://pith.science/pith/AQFDJ76HEQYZILSY47SZ75GL22/action/citation_signature","submit_replication":"https://pith.science/pith/AQFDJ76HEQYZILSY47SZ75GL22/action/replication_record"}},"created_at":"2026-07-05T06:00:25.337480+00:00","updated_at":"2026-07-05T06:00:25.337480+00:00"}