{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LWZ2AVQZAFNRSPCRWB573CV2RE","short_pith_number":"pith:LWZ2AVQZ","schema_version":"1.0","canonical_sha256":"5db3a05619015b193c51b07bfd8aba8900494032f4ba526eae32beb951d98444","source":{"kind":"arxiv","id":"1911.06928","version":2},"attestation_state":"computed","paper":{"title":"Generalized Maximum Causal Entropy for Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kennard Chan, Patrick Jaillet, Tien Mai","submitted_at":"2019-11-16T01:07:23Z","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"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1911.06928","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-16T01:07:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"69d315070523d6c884bb01f8fef882a96fb5b6b32507f0a57ecc42a2892de339","abstract_canon_sha256":"43ab4d9ccd0cf54f2f02b3cc22f212c559afbddff57250e1e27f6c3796ebddb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:43.729160Z","signature_b64":"El/3QwdX9hETKjQhfwfxDUUElOaOmL4gYcgdZxBWr93Lu5+6COGIOcWe57e9RapYCBqNkDwclTbxawDaH4vkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5db3a05619015b193c51b07bfd8aba8900494032f4ba526eae32beb951d98444","last_reissued_at":"2026-07-05T01:27:43.728750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:43.728750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Maximum Causal Entropy for Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kennard Chan, Patrick Jaillet, Tien Mai","submitted_at":"2019-11-16T01:07:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06928","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.06928/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"1911.06928","created_at":"2026-07-05T01:27:43.728820+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.06928v2","created_at":"2026-07-05T01:27:43.728820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06928","created_at":"2026-07-05T01:27:43.728820+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWZ2AVQZAFNR","created_at":"2026-07-05T01:27:43.728820+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWZ2AVQZAFNRSPCR","created_at":"2026-07-05T01:27:43.728820+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWZ2AVQZ","created_at":"2026-07-05T01:27:43.728820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWZ2AVQZAFNRSPCRWB573CV2RE","json":"https://pith.science/pith/LWZ2AVQZAFNRSPCRWB573CV2RE.json","graph_json":"https://pith.science/api/pith-number/LWZ2AVQZAFNRSPCRWB573CV2RE/graph.json","events_json":"https://pith.science/api/pith-number/LWZ2AVQZAFNRSPCRWB573CV2RE/events.json","paper":"https://pith.science/paper/LWZ2AVQZ"},"agent_actions":{"view_html":"https://pith.science/pith/LWZ2AVQZAFNRSPCRWB573CV2RE","download_json":"https://pith.science/pith/LWZ2AVQZAFNRSPCRWB573CV2RE.json","view_paper":"https://pith.science/paper/LWZ2AVQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.06928&json=true","fetch_graph":"https://pith.science/api/pith-number/LWZ2AVQZAFNRSPCRWB573CV2RE/graph.json","fetch_events":"https://pith.science/api/pith-number/LWZ2AVQZAFNRSPCRWB573CV2RE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWZ2AVQZAFNRSPCRWB573CV2RE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWZ2AVQZAFNRSPCRWB573CV2RE/action/storage_attestation","attest_author":"https://pith.science/pith/LWZ2AVQZAFNRSPCRWB573CV2RE/action/author_attestation","sign_citation":"https://pith.science/pith/LWZ2AVQZAFNRSPCRWB573CV2RE/action/citation_signature","submit_replication":"https://pith.science/pith/LWZ2AVQZAFNRSPCRWB573CV2RE/action/replication_record"}},"created_at":"2026-07-05T01:27:43.728820+00:00","updated_at":"2026-07-05T01:27:43.728820+00:00"}