{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NW7QO355FDOIMPT4DC4H6TT2IX","short_pith_number":"pith:NW7QO355","schema_version":"1.0","canonical_sha256":"6dbf076fbd28dc863e7c18b87f4e7a45ca4494b8fbd1baa168edb8940b05e8e5","source":{"kind":"arxiv","id":"2206.01311","version":2},"attestation_state":"computed","paper":{"title":"Learning Soft Constraints From Constrained Expert Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ashish Gaurav, Guiliang Liu, Kasra Rezaee, Pascal Poupart","submitted_at":"2022-06-02T21:45:31Z","abstract_excerpt":"Inverse reinforcement learning (IRL) methods assume that the expert data is generated by an agent optimizing some reward function. However, in many settings, the agent may optimize a reward function subject to some constraints, where the constraints induce behaviors that may be otherwise difficult to express with just a reward function. We consider the setting where the reward function is given, and the constraints are unknown, and propose a method that is able to recover these constraints satisfactorily from the expert data. While previous work has focused on recovering hard constraints, our "},"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":"2206.01311","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-02T21:45:31Z","cross_cats_sorted":[],"title_canon_sha256":"ce9d0c55155d0b17deeb3ae44ef94f6bd2ae070182358af7957be07fcf5a588a","abstract_canon_sha256":"9d651def483d9113ab42968628b61a095870f45e9a249a8af16ab57a7ef83673"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:11.898034Z","signature_b64":"ojRmWBQnHzRUNlTnp4+xUd8Aw/ZKREIEp4cbgn3TxFg2DKjGS1+4PiC8bu+t9otz7UOgxT5HYyJh9T7ZIIuXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dbf076fbd28dc863e7c18b87f4e7a45ca4494b8fbd1baa168edb8940b05e8e5","last_reissued_at":"2026-07-05T06:05:11.897588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:11.897588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Soft Constraints From Constrained Expert Demonstrations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ashish Gaurav, Guiliang Liu, Kasra Rezaee, Pascal Poupart","submitted_at":"2022-06-02T21:45:31Z","abstract_excerpt":"Inverse reinforcement learning (IRL) methods assume that the expert data is generated by an agent optimizing some reward function. However, in many settings, the agent may optimize a reward function subject to some constraints, where the constraints induce behaviors that may be otherwise difficult to express with just a reward function. We consider the setting where the reward function is given, and the constraints are unknown, and propose a method that is able to recover these constraints satisfactorily from the expert data. While previous work has focused on recovering hard constraints, our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01311","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/2206.01311/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":"2206.01311","created_at":"2026-07-05T06:05:11.897651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.01311v2","created_at":"2026-07-05T06:05:11.897651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01311","created_at":"2026-07-05T06:05:11.897651+00:00"},{"alias_kind":"pith_short_12","alias_value":"NW7QO355FDOI","created_at":"2026-07-05T06:05:11.897651+00:00"},{"alias_kind":"pith_short_16","alias_value":"NW7QO355FDOIMPT4","created_at":"2026-07-05T06:05:11.897651+00:00"},{"alias_kind":"pith_short_8","alias_value":"NW7QO355","created_at":"2026-07-05T06:05:11.897651+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/NW7QO355FDOIMPT4DC4H6TT2IX","json":"https://pith.science/pith/NW7QO355FDOIMPT4DC4H6TT2IX.json","graph_json":"https://pith.science/api/pith-number/NW7QO355FDOIMPT4DC4H6TT2IX/graph.json","events_json":"https://pith.science/api/pith-number/NW7QO355FDOIMPT4DC4H6TT2IX/events.json","paper":"https://pith.science/paper/NW7QO355"},"agent_actions":{"view_html":"https://pith.science/pith/NW7QO355FDOIMPT4DC4H6TT2IX","download_json":"https://pith.science/pith/NW7QO355FDOIMPT4DC4H6TT2IX.json","view_paper":"https://pith.science/paper/NW7QO355","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.01311&json=true","fetch_graph":"https://pith.science/api/pith-number/NW7QO355FDOIMPT4DC4H6TT2IX/graph.json","fetch_events":"https://pith.science/api/pith-number/NW7QO355FDOIMPT4DC4H6TT2IX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NW7QO355FDOIMPT4DC4H6TT2IX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NW7QO355FDOIMPT4DC4H6TT2IX/action/storage_attestation","attest_author":"https://pith.science/pith/NW7QO355FDOIMPT4DC4H6TT2IX/action/author_attestation","sign_citation":"https://pith.science/pith/NW7QO355FDOIMPT4DC4H6TT2IX/action/citation_signature","submit_replication":"https://pith.science/pith/NW7QO355FDOIMPT4DC4H6TT2IX/action/replication_record"}},"created_at":"2026-07-05T06:05:11.897651+00:00","updated_at":"2026-07-05T06:05:11.897651+00:00"}