{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LWZ2AVQZAFNRSPCRWB573CV2RE","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":"43ab4d9ccd0cf54f2f02b3cc22f212c559afbddff57250e1e27f6c3796ebddb4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-16T01:07:23Z","title_canon_sha256":"69d315070523d6c884bb01f8fef882a96fb5b6b32507f0a57ecc42a2892de339"},"schema_version":"1.0","source":{"id":"1911.06928","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.06928","created_at":"2026-07-05T01:27:43Z"},{"alias_kind":"arxiv_version","alias_value":"1911.06928v2","created_at":"2026-07-05T01:27:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06928","created_at":"2026-07-05T01:27:43Z"},{"alias_kind":"pith_short_12","alias_value":"LWZ2AVQZAFNR","created_at":"2026-07-05T01:27:43Z"},{"alias_kind":"pith_short_16","alias_value":"LWZ2AVQZAFNRSPCR","created_at":"2026-07-05T01:27:43Z"},{"alias_kind":"pith_short_8","alias_value":"LWZ2AVQZ","created_at":"2026-07-05T01:27:43Z"}],"graph_snapshots":[{"event_id":"sha256:13571c40b8fdae1bdf389ce68ae172748312d7decc8d376994766855eebab817","target":"graph","created_at":"2026-07-05T01:27:43Z","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/1911.06928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of learning from demonstrated trajectories with inverse reinforcement learning (IRL). Motivated by a limitation of the classical maximum entropy model in capturing the structure of the network of states, we propose an IRL model based on a generalized version of the causal entropy maximization problem, which allows us to generate a class of maximum entropy IRL models. Our generalized model has an advantage of being able to recover, in addition to a reward function, another expert's function that would (partially) capture the impact of the connecting structure of the stat","authors_text":"Kennard Chan, Patrick Jaillet, Tien Mai","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-16T01:07:23Z","title":"Generalized Maximum Causal Entropy for Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06928","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":"sha256:9aa9bf67c5a4f6e7341eb67bc5c49013fcc48c6a928946c3cf149eba41f4bbbb","target":"record","created_at":"2026-07-05T01:27:43Z","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":"43ab4d9ccd0cf54f2f02b3cc22f212c559afbddff57250e1e27f6c3796ebddb4","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-16T01:07:23Z","title_canon_sha256":"69d315070523d6c884bb01f8fef882a96fb5b6b32507f0a57ecc42a2892de339"},"schema_version":"1.0","source":{"id":"1911.06928","kind":"arxiv","version":2}},"canonical_sha256":"5db3a05619015b193c51b07bfd8aba8900494032f4ba526eae32beb951d98444","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5db3a05619015b193c51b07bfd8aba8900494032f4ba526eae32beb951d98444","first_computed_at":"2026-07-05T01:27:43.728750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:27:43.728750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"El/3QwdX9hETKjQhfwfxDUUElOaOmL4gYcgdZxBWr93Lu5+6COGIOcWe57e9RapYCBqNkDwclTbxawDaH4vkAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:27:43.729160Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.06928","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9aa9bf67c5a4f6e7341eb67bc5c49013fcc48c6a928946c3cf149eba41f4bbbb","sha256:13571c40b8fdae1bdf389ce68ae172748312d7decc8d376994766855eebab817"],"state_sha256":"ab24332d1f152f4631a8b56f508b8b253b95bbba7050858525f47970a23500e1"}