{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6ZPHRC4IIN6XFCUICOEVAEYWSL","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":"959d24111281062edf0d194a5078ec028dafaa220226965ff2bd248270c2555c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T23:38:47Z","title_canon_sha256":"fce1e6178aaf0d0a2c5a26bd3b465e37858374623a9b24fdc42e42c1231cb19f"},"schema_version":"1.0","source":{"id":"2010.03691","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.03691","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"arxiv_version","alias_value":"2010.03691v2","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03691","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"pith_short_12","alias_value":"6ZPHRC4IIN6X","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"pith_short_16","alias_value":"6ZPHRC4IIN6XFCUI","created_at":"2026-07-05T01:56:44Z"},{"alias_kind":"pith_short_8","alias_value":"6ZPHRC4I","created_at":"2026-07-05T01:56:44Z"}],"graph_snapshots":[{"event_id":"sha256:05b5b2cbbc41882f3bc8ec0ea30c2aafc29e167a36b79edca79f90f3502eca51","target":"graph","created_at":"2026-07-05T01:56:44Z","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/2010.03691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inverse Reinforcement Learning (IRL) aims to facilitate a learner's ability to imitate expert behavior by acquiring reward functions that explain the expert's decisions. Regularized IRL applies strongly convex regularizers to the learner's policy in order to avoid the expert's behavior being rationalized by arbitrary constant rewards, also known as degenerate solutions. We propose tractable solutions, and practical methods to obtain them, for regularized IRL. Current methods are restricted to the maximum-entropy IRL framework, limiting them to Shannon-entropy regularizers, as well as proposing","authors_text":"Chen-Yang Su, Derek Nowrouzezahrai, Joelle Pineau, Paul Barde, Thang Doan, Wonseok Jeon","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T23:38:47Z","title":"Regularized Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03691","kind":"arxiv","version":2},"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":"sha256:4412d0d2985be1a327b76c11ca9d0fccebc7cadcbf6958841a3ec8f18db84feb","target":"record","created_at":"2026-07-05T01:56:44Z","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":"959d24111281062edf0d194a5078ec028dafaa220226965ff2bd248270c2555c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T23:38:47Z","title_canon_sha256":"fce1e6178aaf0d0a2c5a26bd3b465e37858374623a9b24fdc42e42c1231cb19f"},"schema_version":"1.0","source":{"id":"2010.03691","kind":"arxiv","version":2}},"canonical_sha256":"f65e788b88437d728a88138950131692e7f88c4060e98065a8485394521ec25b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f65e788b88437d728a88138950131692e7f88c4060e98065a8485394521ec25b","first_computed_at":"2026-07-05T01:56:44.501565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:44.501565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"77Ch0IdtUZ7mRpH5u0Eo8z8bwEE2lywoD71J6IKMzVA6mvqEddEwOLOSEspEr7UIxitTBE4XAzu1YmCJtU71DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:44.501998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.03691","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4412d0d2985be1a327b76c11ca9d0fccebc7cadcbf6958841a3ec8f18db84feb","sha256:05b5b2cbbc41882f3bc8ec0ea30c2aafc29e167a36b79edca79f90f3502eca51"],"state_sha256":"ddce13d9fd9976ca9cf2c53ca49611bc425f1ca2f61fb0a0f90521bba6758d64"}