{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZDMFOJJYBH5FHPZBEZA3NIBUOY","short_pith_number":"pith:ZDMFOJJY","schema_version":"1.0","canonical_sha256":"c8d857253809fa53bf212641b6a03476145baa21bea1e18fb9086bacbb689665","source":{"kind":"arxiv","id":"2002.09043","version":1},"attestation_state":"computed","paper":{"title":"oIRL: Robust Adversarial Inverse Reinforcement Learning with Temporally Extended Actions","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Venuto, Doina Precup, Gavin McCracken, Jhelum Chakravorty, Junhao Wang, Leonard Boussioux","submitted_at":"2020-02-20T22:21:41Z","abstract_excerpt":"Explicit engineering of reward functions for given environments has been a major hindrance to reinforcement learning methods. While Inverse Reinforcement Learning (IRL) is a solution to recover reward functions from demonstrations only, these learned rewards are generally heavily \\textit{entangled} with the dynamics of the environment and therefore not portable or \\emph{robust} to changing environments. Modern adversarial methods have yielded some success in reducing reward entanglement in the IRL setting. In this work, we leverage one such method, Adversarial Inverse Reinforcement Learning (A"},"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":"2002.09043","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T22:21:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c3d54e720217cc4cd0a9c4f0a97f162f68651cb7a623a24672b496243e301fe7","abstract_canon_sha256":"e0806f62f6705eacbf81cf94d15504c3458d33cd17635ac9e6c6dd9b9badf662"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:44.884847Z","signature_b64":"+Jv2y9oaErO7tXv7XwTxoxA/dPu5lmxIuDOi/T/s69eriz42B+NVHhyM99kT1VW6LZzDs/UmWurgFy0Q5usFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8d857253809fa53bf212641b6a03476145baa21bea1e18fb9086bacbb689665","last_reissued_at":"2026-07-05T00:42:44.884455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:44.884455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"oIRL: Robust Adversarial Inverse Reinforcement Learning with Temporally Extended Actions","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Venuto, Doina Precup, Gavin McCracken, Jhelum Chakravorty, Junhao Wang, Leonard Boussioux","submitted_at":"2020-02-20T22:21:41Z","abstract_excerpt":"Explicit engineering of reward functions for given environments has been a major hindrance to reinforcement learning methods. While Inverse Reinforcement Learning (IRL) is a solution to recover reward functions from demonstrations only, these learned rewards are generally heavily \\textit{entangled} with the dynamics of the environment and therefore not portable or \\emph{robust} to changing environments. Modern adversarial methods have yielded some success in reducing reward entanglement in the IRL setting. In this work, we leverage one such method, Adversarial Inverse Reinforcement Learning (A"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09043","kind":"arxiv","version":1},"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/2002.09043/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":"2002.09043","created_at":"2026-07-05T00:42:44.884512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.09043v1","created_at":"2026-07-05T00:42:44.884512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09043","created_at":"2026-07-05T00:42:44.884512+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDMFOJJYBH5F","created_at":"2026-07-05T00:42:44.884512+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDMFOJJYBH5FHPZB","created_at":"2026-07-05T00:42:44.884512+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDMFOJJY","created_at":"2026-07-05T00:42:44.884512+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/ZDMFOJJYBH5FHPZBEZA3NIBUOY","json":"https://pith.science/pith/ZDMFOJJYBH5FHPZBEZA3NIBUOY.json","graph_json":"https://pith.science/api/pith-number/ZDMFOJJYBH5FHPZBEZA3NIBUOY/graph.json","events_json":"https://pith.science/api/pith-number/ZDMFOJJYBH5FHPZBEZA3NIBUOY/events.json","paper":"https://pith.science/paper/ZDMFOJJY"},"agent_actions":{"view_html":"https://pith.science/pith/ZDMFOJJYBH5FHPZBEZA3NIBUOY","download_json":"https://pith.science/pith/ZDMFOJJYBH5FHPZBEZA3NIBUOY.json","view_paper":"https://pith.science/paper/ZDMFOJJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.09043&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDMFOJJYBH5FHPZBEZA3NIBUOY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDMFOJJYBH5FHPZBEZA3NIBUOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDMFOJJYBH5FHPZBEZA3NIBUOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDMFOJJYBH5FHPZBEZA3NIBUOY/action/storage_attestation","attest_author":"https://pith.science/pith/ZDMFOJJYBH5FHPZBEZA3NIBUOY/action/author_attestation","sign_citation":"https://pith.science/pith/ZDMFOJJYBH5FHPZBEZA3NIBUOY/action/citation_signature","submit_replication":"https://pith.science/pith/ZDMFOJJYBH5FHPZBEZA3NIBUOY/action/replication_record"}},"created_at":"2026-07-05T00:42:44.884512+00:00","updated_at":"2026-07-05T00:42:44.884512+00:00"}