{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:O7B5YLTXHETBLKN46LM7VUGJAW","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":"6e4077b18048893b15ef33fab65884576c4699741ec97f72c01c5fee44c588c0","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-18T15:02:28Z","title_canon_sha256":"d6a82266434cab854ab2843def4aa29b72b448e8ec86b360b78529ef5da3715b"},"schema_version":"1.0","source":{"id":"1206.4617","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.4617","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"arxiv_version","alias_value":"1206.4617v1","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.4617","created_at":"2026-05-18T03:53:04Z"},{"alias_kind":"pith_short_12","alias_value":"O7B5YLTXHETB","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_16","alias_value":"O7B5YLTXHETBLKN4","created_at":"2026-05-18T12:27:16Z"},{"alias_kind":"pith_short_8","alias_value":"O7B5YLTX","created_at":"2026-05-18T12:27:16Z"}],"graph_snapshots":[{"event_id":"sha256:5e434edf2268085e639ada631e19220e1783b75b58ad034cbe7fa06471b7d4ea","target":"graph","created_at":"2026-05-18T03:53:04Z","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"},"paper":{"abstract_excerpt":"Inverse optimal control, also known as inverse reinforcement learning, is the problem of recovering an unknown reward function in a Markov decision process from expert demonstrations of the optimal policy. We introduce a probabilistic inverse optimal control algorithm that scales gracefully with task dimensionality, and is suitable for large, continuous domains where even computing a full policy is impractical. By using a local approximation of the reward function, our method can also drop the assumption that the demonstrations are globally optimal, requiring only local optimality. This allows","authors_text":"Sergey Levine (Stanford University), Vladlen Koltun (Stanford University)","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-18T15:02:28Z","title":"Continuous Inverse Optimal Control with Locally Optimal Examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.4617","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:a31e044abcaaba22bc29ab97627acd9cbc57f41b994065d4d353688337039e5d","target":"record","created_at":"2026-05-18T03:53:04Z","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":"6e4077b18048893b15ef33fab65884576c4699741ec97f72c01c5fee44c588c0","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-18T15:02:28Z","title_canon_sha256":"d6a82266434cab854ab2843def4aa29b72b448e8ec86b360b78529ef5da3715b"},"schema_version":"1.0","source":{"id":"1206.4617","kind":"arxiv","version":1}},"canonical_sha256":"77c3dc2e77392615a9bcf2d9fad0c9059ad0156a24882dd425a26d42bc8840d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77c3dc2e77392615a9bcf2d9fad0c9059ad0156a24882dd425a26d42bc8840d9","first_computed_at":"2026-05-18T03:53:04.593642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:53:04.593642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fo3UN3xXdMUchA3J12ahEHJlbsjmNlCHyealmzFRnHcmqJYMNG/Hr+U1bJTqdM1gVw0G8N42nPUy/DIw4m8yCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:53:04.594137Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.4617","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a31e044abcaaba22bc29ab97627acd9cbc57f41b994065d4d353688337039e5d","sha256:5e434edf2268085e639ada631e19220e1783b75b58ad034cbe7fa06471b7d4ea"],"state_sha256":"9f4f57968bdaf2f535c902fa23280bb94bed393d3bed0835636700276c4ce0f2"}