{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SM3GVPP5VG3WJAYXAT4V47MSGM","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":"991689b7e8d3b0b96608e5087e54bfe435d281fcd957559a4c84ddbf52779fa4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T18:29:13Z","title_canon_sha256":"e3383149f2181c4573609c96e0d60cc6154d97e08e2dad6e16e3146ea0122025"},"schema_version":"1.0","source":{"id":"2006.13258","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.13258","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"arxiv_version","alias_value":"2006.13258v6","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.13258","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"pith_short_12","alias_value":"SM3GVPP5VG3W","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"pith_short_16","alias_value":"SM3GVPP5VG3WJAYX","created_at":"2026-07-05T02:32:32Z"},{"alias_kind":"pith_short_8","alias_value":"SM3GVPP5","created_at":"2026-07-05T02:32:32Z"}],"graph_snapshots":[{"event_id":"sha256:979a246eca6ff1cd4ca67f5d8335cbe20e8e5df1f20e11c5e06b3cdfb055db95","target":"graph","created_at":"2026-07-05T02:32:32Z","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/2006.13258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial Imitation Learning alternates between learning a discriminator -- which tells apart expert's demonstrations from generated ones -- and a generator's policy to produce trajectories that can fool this discriminator. This alternated optimization is known to be delicate in practice since it compounds unstable adversarial training with brittle and sample-inefficient reinforcement learning. We propose to remove the burden of the policy optimization steps by leveraging a novel discriminator formulation. Specifically, our discriminator is explicitly conditioned on two policies: the one fro","authors_text":"Christopher Pal, Derek Nowrouzezahrai, Joelle Pineau, Julien Roy, Paul Barde, Wonseok Jeon","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T18:29:13Z","title":"Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.13258","kind":"arxiv","version":6},"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":"sha256:30f8249f3c2332a0a571cec9a119aa65c8094c71aaf4db43ae7852077cbd21bd","target":"record","created_at":"2026-07-05T02:32:32Z","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":"991689b7e8d3b0b96608e5087e54bfe435d281fcd957559a4c84ddbf52779fa4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T18:29:13Z","title_canon_sha256":"e3383149f2181c4573609c96e0d60cc6154d97e08e2dad6e16e3146ea0122025"},"schema_version":"1.0","source":{"id":"2006.13258","kind":"arxiv","version":6}},"canonical_sha256":"93366abdfda9b764831704f95e7d92330f5192b58fc38660b5e4ab0345c96d18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93366abdfda9b764831704f95e7d92330f5192b58fc38660b5e4ab0345c96d18","first_computed_at":"2026-07-05T02:32:32.625168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:32.625168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TznUnHkorYsd8qkctuvOGha7FWNYCPT19VhCH5I7MmvWZTyqf7/v8jAZ46ijBW27I9fLwtgcTwO9hgxeVwIPDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:32.625735Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.13258","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30f8249f3c2332a0a571cec9a119aa65c8094c71aaf4db43ae7852077cbd21bd","sha256:979a246eca6ff1cd4ca67f5d8335cbe20e8e5df1f20e11c5e06b3cdfb055db95"],"state_sha256":"7d4004befcf790197544e74fb138551b1d432eb63722dbb641dc95eea9765d12"}