{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZDMFOJJYBH5FHPZBEZA3NIBUOY","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":"e0806f62f6705eacbf81cf94d15504c3458d33cd17635ac9e6c6dd9b9badf662","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T22:21:41Z","title_canon_sha256":"c3d54e720217cc4cd0a9c4f0a97f162f68651cb7a623a24672b496243e301fe7"},"schema_version":"1.0","source":{"id":"2002.09043","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09043","created_at":"2026-07-05T00:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09043v1","created_at":"2026-07-05T00:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09043","created_at":"2026-07-05T00:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZDMFOJJYBH5F","created_at":"2026-07-05T00:42:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZDMFOJJYBH5FHPZB","created_at":"2026-07-05T00:42:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZDMFOJJY","created_at":"2026-07-05T00:42:44Z"}],"graph_snapshots":[{"event_id":"sha256:421e0710706df5893588757c4a5219298eb543e4f217a4952f7825b5fb09ad24","target":"graph","created_at":"2026-07-05T00:42:44Z","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/2002.09043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Venuto, Doina Precup, Gavin McCracken, Jhelum Chakravorty, Junhao Wang, Leonard Boussioux","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T22:21:41Z","title":"oIRL: Robust Adversarial Inverse Reinforcement Learning with Temporally Extended Actions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09043","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":"sha256:04fa6c161464accec3c8c6ffec7e32e74b6cf15f6fcb91160ec8dfbbf834fae7","target":"record","created_at":"2026-07-05T00:42:44Z","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":"e0806f62f6705eacbf81cf94d15504c3458d33cd17635ac9e6c6dd9b9badf662","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-20T22:21:41Z","title_canon_sha256":"c3d54e720217cc4cd0a9c4f0a97f162f68651cb7a623a24672b496243e301fe7"},"schema_version":"1.0","source":{"id":"2002.09043","kind":"arxiv","version":1}},"canonical_sha256":"c8d857253809fa53bf212641b6a03476145baa21bea1e18fb9086bacbb689665","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8d857253809fa53bf212641b6a03476145baa21bea1e18fb9086bacbb689665","first_computed_at":"2026-07-05T00:42:44.884455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:42:44.884455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Jv2y9oaErO7tXv7XwTxoxA/dPu5lmxIuDOi/T/s69eriz42B+NVHhyM99kT1VW6LZzDs/UmWurgFy0Q5usFCw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:42:44.884847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.09043","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04fa6c161464accec3c8c6ffec7e32e74b6cf15f6fcb91160ec8dfbbf834fae7","sha256:421e0710706df5893588757c4a5219298eb543e4f217a4952f7825b5fb09ad24"],"state_sha256":"cd4d15a022e086efc7717720645e8a66baf422267ce3b1afcc7e2088d242ac30"}