{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CZU2QIMDK4Y3SFM5RI27BTRR77","short_pith_number":"pith:CZU2QIMD","schema_version":"1.0","canonical_sha256":"1669a821835731b9159d8a35f0ce31ffd899485ca3491db02ba99ba1bd27975f","source":{"kind":"arxiv","id":"2605.14599","version":1},"attestation_state":"computed","paper":{"title":"Fast Rates for Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Min-Max-IRL with linear rewards achieves fast O(n^{-1}) rates for KL divergence and parameter error.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Schlaginhaufen, Maryam Kamgarpour","submitted_at":"2026-05-14T09:07:31Z","abstract_excerpt":"We establish novel structural and statistical results for entropy-regularized min-max inverse reinforcement learning (Min-Max-IRL) with linear reward classes in finite-horizon MDPs with Borel state and action spaces. On the structural side, we show that maximum likelihood estimation (MLE) and Min-Max-IRL are equivalent at the population level, and at the empirical level under deterministic dynamics. On the statistical side, exploiting pseudo-self-concordance of the Min-Max-IRL loss, we prove that both the trajectory-level KL divergence and the squared parameter error in the Hessian norm decay "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T09:07:31Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"147f5f120acf21e3e740194c0d945d73eee02f7a461d526f4344029256caaeb2","abstract_canon_sha256":"1b54a95d9c9568780923126408f03216921fd62ad2ceaee949651603d7664232"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:04.273010Z","signature_b64":"L6kpdMsyoWgM0r2SLpjbja3iYLuX6dgO+F1eo+vp17pgc7LQwC0gO95dUmsXLUFa26QM7KDk7PCP459WjHaEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1669a821835731b9159d8a35f0ce31ffd899485ca3491db02ba99ba1bd27975f","last_reissued_at":"2026-05-17T23:39:04.272455Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:04.272455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast Rates for Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Min-Max-IRL with linear rewards achieves fast O(n^{-1}) rates for KL divergence and parameter error.","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Schlaginhaufen, Maryam Kamgarpour","submitted_at":"2026-05-14T09:07:31Z","abstract_excerpt":"We establish novel structural and statistical results for entropy-regularized min-max inverse reinforcement learning (Min-Max-IRL) with linear reward classes in finite-horizon MDPs with Borel state and action spaces. On the structural side, we show that maximum likelihood estimation (MLE) and Min-Max-IRL are equivalent at the population level, and at the empirical level under deterministic dynamics. On the statistical side, exploiting pseudo-self-concordance of the Min-Max-IRL loss, we prove that both the trajectory-level KL divergence and the squared parameter error in the Hessian norm decay "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"exploiting pseudo-self-concordance of the Min-Max-IRL loss, we prove that both the trajectory-level KL divergence and the squared parameter error in the Hessian norm decay at the fast rate O(n^{-1})","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The Min-Max-IRL loss is pseudo-self-concordant (invoked to obtain the fast rates); the paper also relies on linear reward classes and finite-horizon structure.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Entropy-regularized Min-Max-IRL achieves O(n^{-1}) rates for trajectory-level KL divergence and squared parameter error in the Hessian norm under misspecification in Borel MDPs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Min-Max-IRL with linear rewards achieves fast O(n^{-1}) rates for KL divergence and parameter error.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bfa8145161c9336b7e436930a09c57512a8cb7955123c678a607181eef9fee97"},"source":{"id":"2605.14599","kind":"arxiv","version":1},"verdict":{"id":"1f54522c-080f-4431-8dd7-6a9ef9846f93","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:00:25.431896Z","strongest_claim":"exploiting pseudo-self-concordance of the Min-Max-IRL loss, we prove that both the trajectory-level KL divergence and the squared parameter error in the Hessian norm decay at the fast rate O(n^{-1})","one_line_summary":"Entropy-regularized Min-Max-IRL achieves O(n^{-1}) rates for trajectory-level KL divergence and squared parameter error in the Hessian norm under misspecification in Borel MDPs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The Min-Max-IRL loss is pseudo-self-concordant (invoked to obtain the fast rates); the paper also relies on linear reward classes and finite-horizon structure.","pith_extraction_headline":"Min-Max-IRL with linear rewards achieves fast O(n^{-1}) rates for KL divergence and parameter error."},"references":{"count":14,"sample":[{"doi":"","year":null,"title":"Ifβ >0, thenπ=π⋆ r if and only ifAπ t,r(s,a) = 0for all(t,s)andν-a.e.a∈A","work_id":"348aead3-28f6-4a73-aad0-6efa6d362dce","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1999,"title":"9 Proof.Inpart 1, the implicationπ=π⋆ r =⇒Aπ t,r = 0ν-a.s","work_id":"79ae2fb4-bca0-4204-a96d-1fde78f1ee1a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"For allα∈[0,1], e−αSH(θ0)⪯H(θα)⪯eαSH(θ0).(15)","work_id":"c5900a65-3f16-457c-a12a-d782f5f071c6","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Then ψ(−S)∥∆∥2 H(θ0) ≤DJ⋆(θ1,θ0)≤ψ(S)∥∆∥2 H(θ0)","work_id":"57d2e3a1-9581-4113-b9f8-9f247bc13db6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Then χ(−S)∥∆∥2 H(θ0) ≤DJ⋆(θ1,θ0) +DJ⋆(θ0,θ1) =⟨∆,∇J⋆(θ1)−∇J⋆(θ0)⟩ ≤χ(S)∥∆∥2 H(θ0)","work_id":"ec733bd1-90de-4b61-b6dd-10f9ad17f874","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":14,"snapshot_sha256":"650b51d63afe485d146a8caad391eb3eccf020e412d3a0004a1b8d9b15c52489","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"92bda282e56769e5ba3a253b5ec0780111c2c53fab76e7b7417df882716967a2"},"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":"2605.14599","created_at":"2026-05-17T23:39:04.272544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14599v1","created_at":"2026-05-17T23:39:04.272544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14599","created_at":"2026-05-17T23:39:04.272544+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZU2QIMDK4Y3","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZU2QIMDK4Y3SFM5","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZU2QIMD","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZU2QIMDK4Y3SFM5RI27BTRR77","json":"https://pith.science/pith/CZU2QIMDK4Y3SFM5RI27BTRR77.json","graph_json":"https://pith.science/api/pith-number/CZU2QIMDK4Y3SFM5RI27BTRR77/graph.json","events_json":"https://pith.science/api/pith-number/CZU2QIMDK4Y3SFM5RI27BTRR77/events.json","paper":"https://pith.science/paper/CZU2QIMD"},"agent_actions":{"view_html":"https://pith.science/pith/CZU2QIMDK4Y3SFM5RI27BTRR77","download_json":"https://pith.science/pith/CZU2QIMDK4Y3SFM5RI27BTRR77.json","view_paper":"https://pith.science/paper/CZU2QIMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14599&json=true","fetch_graph":"https://pith.science/api/pith-number/CZU2QIMDK4Y3SFM5RI27BTRR77/graph.json","fetch_events":"https://pith.science/api/pith-number/CZU2QIMDK4Y3SFM5RI27BTRR77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZU2QIMDK4Y3SFM5RI27BTRR77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZU2QIMDK4Y3SFM5RI27BTRR77/action/storage_attestation","attest_author":"https://pith.science/pith/CZU2QIMDK4Y3SFM5RI27BTRR77/action/author_attestation","sign_citation":"https://pith.science/pith/CZU2QIMDK4Y3SFM5RI27BTRR77/action/citation_signature","submit_replication":"https://pith.science/pith/CZU2QIMDK4Y3SFM5RI27BTRR77/action/replication_record"}},"created_at":"2026-05-17T23:39:04.272544+00:00","updated_at":"2026-05-17T23:39:04.272544+00:00"}