{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OK6LKBRCWJKG4LXTUIACYDUKIT","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":"6e5d2b7e00dae351f414f0a0057d31359fd790fad66c315afbc64c1118e2af59","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-13T12:45:52Z","title_canon_sha256":"3c772a7b4149d7deb761405d05ea3e0c93f8ad0857a1f685c8faf74c695301c0"},"schema_version":"1.0","source":{"id":"2009.05990","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.05990","created_at":"2026-07-05T01:35:03Z"},{"alias_kind":"arxiv_version","alias_value":"2009.05990v1","created_at":"2026-07-05T01:35:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.05990","created_at":"2026-07-05T01:35:03Z"},{"alias_kind":"pith_short_12","alias_value":"OK6LKBRCWJKG","created_at":"2026-07-05T01:35:03Z"},{"alias_kind":"pith_short_16","alias_value":"OK6LKBRCWJKG4LXT","created_at":"2026-07-05T01:35:03Z"},{"alias_kind":"pith_short_8","alias_value":"OK6LKBRC","created_at":"2026-07-05T01:35:03Z"}],"graph_snapshots":[{"event_id":"sha256:a020f29eb197a7aa3e609ee1f71f837a65085b765a04bda87476ef3871e322e9","target":"graph","created_at":"2026-07-05T01:35:03Z","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/2009.05990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation learning (IL) aims to mimic the behavior of an expert policy in a sequential decision-making problem given only demonstrations. In this paper, we focus on understanding the minimax statistical limits of IL in episodic Markov Decision Processes (MDPs). We first consider the setting where the learner is provided a dataset of $N$ expert trajectories ahead of time, and cannot interact with the MDP. Here, we show that the policy which mimics the expert whenever possible is in expectation $\\lesssim \\frac{|\\mathcal{S}| H^2 \\log (N)}{N}$ suboptimal compared to the value of the expert, even w","authors_text":"Jiantao Jiao, Kannan Ramachandran, Lin F. Yang, Nived Rajaraman","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-13T12:45:52Z","title":"Toward the Fundamental Limits of Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.05990","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":"sha256:7ef3473d58c3123a849183268b299ab2c9365f5c3eacc0e810df6c3113357d7c","target":"record","created_at":"2026-07-05T01:35:03Z","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":"6e5d2b7e00dae351f414f0a0057d31359fd790fad66c315afbc64c1118e2af59","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-13T12:45:52Z","title_canon_sha256":"3c772a7b4149d7deb761405d05ea3e0c93f8ad0857a1f685c8faf74c695301c0"},"schema_version":"1.0","source":{"id":"2009.05990","kind":"arxiv","version":1}},"canonical_sha256":"72bcb50622b2546e2ef3a2002c0e8a44dc59c1a00f21bc05329e95f6dc34f95f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72bcb50622b2546e2ef3a2002c0e8a44dc59c1a00f21bc05329e95f6dc34f95f","first_computed_at":"2026-07-05T01:35:03.321037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:35:03.321037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pM0/q5zlBoFrui41WqnrA4wghn114KN4IkJ55CJxMmVWm9dyRFdbXSoxjAuYUeT5YCKaKHG44gOIzsjdqY6SBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:35:03.321425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.05990","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ef3473d58c3123a849183268b299ab2c9365f5c3eacc0e810df6c3113357d7c","sha256:a020f29eb197a7aa3e609ee1f71f837a65085b765a04bda87476ef3871e322e9"],"state_sha256":"e9d01104dfe7febfb02ae86f70ddbf976c374dccf328d5c9a3e385d0fa0f9f48"}