{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:E66MOGKNKC3ELBDVBNLB5FHHLZ","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":"24f454bf5025829ada9853b7fd62d3d6f2f3c465f413cd95555589c3af7e7a5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T16:21:10Z","title_canon_sha256":"bba54f9bec1056a49bb9da3f99d26918cdbbde5d4dfa07ec078912bc1315929c"},"schema_version":"1.0","source":{"id":"2304.12966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.12966","created_at":"2026-07-05T06:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2304.12966v1","created_at":"2026-07-05T06:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12966","created_at":"2026-07-05T06:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"E66MOGKNKC3E","created_at":"2026-07-05T06:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"E66MOGKNKC3ELBDV","created_at":"2026-07-05T06:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"E66MOGKN","created_at":"2026-07-05T06:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:2a89b75f9b1bb64d80e44df65219cbe6dcf3c6f36c44da2c61ddb15f70e0a070","target":"graph","created_at":"2026-07-05T06:04:22Z","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/2304.12966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inverse reinforcement learning (IRL) denotes a powerful family of algorithms for recovering a reward function justifying the behavior demonstrated by an expert agent. A well-known limitation of IRL is the ambiguity in the choice of the reward function, due to the existence of multiple rewards that explain the observed behavior. This limitation has been recently circumvented by formulating IRL as the problem of estimating the feasible reward set, i.e., the region of the rewards compatible with the expert's behavior. In this paper, we make a step towards closing the theory gap of IRL in the case","authors_text":"Alberto Maria Metelli, Filippo Lazzati, Marcello Restelli","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T16:21:10Z","title":"Towards Theoretical Understanding of Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12966","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":"sha256:193df98fb734345f6581ff4bda4a35e42281009127086a9971ffe43cab68d87e","target":"record","created_at":"2026-07-05T06:04:22Z","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":"24f454bf5025829ada9853b7fd62d3d6f2f3c465f413cd95555589c3af7e7a5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T16:21:10Z","title_canon_sha256":"bba54f9bec1056a49bb9da3f99d26918cdbbde5d4dfa07ec078912bc1315929c"},"schema_version":"1.0","source":{"id":"2304.12966","kind":"arxiv","version":1}},"canonical_sha256":"27bcc7194d50b64584750b561e94e75e4c9a84af677658a4799a343e545b817d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27bcc7194d50b64584750b561e94e75e4c9a84af677658a4799a343e545b817d","first_computed_at":"2026-07-05T06:04:22.852899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:22.852899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K3KJiYTrhEj/xBn3FuHbXoF6+DCm3vNeX8zbZERCF3RII2LBeWO/Qt/t1rlxBZNDDjCTUNADYaPqhaIvt75WCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:22.853309Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.12966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:193df98fb734345f6581ff4bda4a35e42281009127086a9971ffe43cab68d87e","sha256:2a89b75f9b1bb64d80e44df65219cbe6dcf3c6f36c44da2c61ddb15f70e0a070"],"state_sha256":"4f518f40836ac757a1f7216f1454ac3b35058ded07c465e9881d88be6c3b373a"}