{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LOXRHV7ZOVDKYDG55RMLFCNJLN","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":"27f40b08956757b5ff9622c42a1917ab47567f6a58be7e05b3e60126a0ac6df8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-28T20:55:31Z","title_canon_sha256":"6bd9a6163dd7a869c2867263f8cfad3995ad8e2adba1bee4ba1394bfb68c3d24"},"schema_version":"1.0","source":{"id":"2006.16785","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.16785","created_at":"2026-07-05T07:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2006.16785v4","created_at":"2026-07-05T07:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16785","created_at":"2026-07-05T07:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"LOXRHV7ZOVDK","created_at":"2026-07-05T07:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"LOXRHV7ZOVDKYDG5","created_at":"2026-07-05T07:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"LOXRHV7Z","created_at":"2026-07-05T07:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:45908bbd05feda7d19ca3cfdf1dfad20d5ea453f7c8c94a885ab8c5b90f6266e","target":"graph","created_at":"2026-07-05T07:04:40Z","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/2006.16785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the recent success of reinforcement learning in various domains, these approaches remain, for the most part, deterringly sensitive to hyper-parameters and are often riddled with essential engineering feats allowing their success. We consider the case of off-policy generative adversarial imitation learning, and perform an in-depth review, qualitative and quantitative, of the method. We show that forcing the learned reward function to be local Lipschitz-continuous is a sine qua non condition for the method to perform well. We then study the effects of this necessary condition and provide","authors_text":"Alexandros Kalousis, Lionel Blond\\'e, Pablo Strasser","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-28T20:55:31Z","title":"Lipschitzness Is All You Need To Tame Off-policy Generative Adversarial Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16785","kind":"arxiv","version":4},"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":"sha256:38ee7ac3fc87129bd6b574e7775ef89dd52ea5d1a8613f333d96de19c272738d","target":"record","created_at":"2026-07-05T07:04:40Z","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":"27f40b08956757b5ff9622c42a1917ab47567f6a58be7e05b3e60126a0ac6df8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-28T20:55:31Z","title_canon_sha256":"6bd9a6163dd7a869c2867263f8cfad3995ad8e2adba1bee4ba1394bfb68c3d24"},"schema_version":"1.0","source":{"id":"2006.16785","kind":"arxiv","version":4}},"canonical_sha256":"5baf13d7f97546ac0cddec58b289a95b601e9806e932ced254091691f9806b16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5baf13d7f97546ac0cddec58b289a95b601e9806e932ced254091691f9806b16","first_computed_at":"2026-07-05T07:04:40.171128Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:40.171128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"of2BLaZuhHuYvXpFZakm8NLTIwdfqC6zrW6GwLcSEW2VX2MEGWytBGGKRpcgLwZJl6bUAiGB1GoJjQI4VfOvAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:40.171629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.16785","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38ee7ac3fc87129bd6b574e7775ef89dd52ea5d1a8613f333d96de19c272738d","sha256:45908bbd05feda7d19ca3cfdf1dfad20d5ea453f7c8c94a885ab8c5b90f6266e"],"state_sha256":"4276588d00496acb46e76c5de40dbe16c0cc33e6613495316c456a9f19b7aecb"}