{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4WSYAINHC6JD6RO7WZN6TDMWDT","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":"caeb7c9d7c8bb05f93de91f87a1321c9ecb69230caaad60a2d4dde18f8fd5d7b","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-05T04:49:58Z","title_canon_sha256":"3251e9d32c2d5cb691d096960510a66015aaff6cf32c9793cb1bf6df4c4bdbbc"},"schema_version":"1.0","source":{"id":"2206.02095","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02095","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02095v4","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02095","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"pith_short_12","alias_value":"4WSYAINHC6JD","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"pith_short_16","alias_value":"4WSYAINHC6JD6RO7","created_at":"2026-07-05T05:21:01Z"},{"alias_kind":"pith_short_8","alias_value":"4WSYAINH","created_at":"2026-07-05T05:21:01Z"}],"graph_snapshots":[{"event_id":"sha256:741ec6a5d14c074e12ed20e8f2b98b442ed9cd1f3a90cbda0961e07c2a201e53","target":"graph","created_at":"2026-07-05T05:21:01Z","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/2206.02095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial Imitation Learning (AIL) is a class of popular state-of-the-art Imitation Learning algorithms commonly used in robotics. In AIL, an artificial adversary's misclassification is used as a reward signal that is optimized by any standard Reinforcement Learning (RL) algorithm. Unlike most RL settings, the reward in AIL is $differentiable$ but current model-free RL algorithms do not make use of this property to train a policy. The reward is AIL is also shaped since it comes from an adversary. We leverage the differentiability property of the shaped AIL reward function and formulate a cla","authors_text":"Ankur Deka, Changliu Liu, Katia Sycara","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-05T04:49:58Z","title":"ARC - Actor Residual Critic for Adversarial Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02095","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:d54a4a24faa20c5682904969acd289da6bd44bc574105f1cab647ded2f143d19","target":"record","created_at":"2026-07-05T05:21:01Z","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":"caeb7c9d7c8bb05f93de91f87a1321c9ecb69230caaad60a2d4dde18f8fd5d7b","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-05T04:49:58Z","title_canon_sha256":"3251e9d32c2d5cb691d096960510a66015aaff6cf32c9793cb1bf6df4c4bdbbc"},"schema_version":"1.0","source":{"id":"2206.02095","kind":"arxiv","version":4}},"canonical_sha256":"e5a58021a717923f45dfb65be98d961cdb304246c32d53c2f9f6cb597b7a3fac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e5a58021a717923f45dfb65be98d961cdb304246c32d53c2f9f6cb597b7a3fac","first_computed_at":"2026-07-05T05:21:01.579916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:21:01.579916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZJnpm7TOSQo24HfD3b3O81SQ3ZuXOmVPy/Y7ytfdsJfumZFkMffncMBIFkcidYjpdXi5r6SFFoYdAnjw35KSAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:21:01.580375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.02095","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d54a4a24faa20c5682904969acd289da6bd44bc574105f1cab647ded2f143d19","sha256:741ec6a5d14c074e12ed20e8f2b98b442ed9cd1f3a90cbda0961e07c2a201e53"],"state_sha256":"2387a3dbb3eb1411183352f1f8298f9fc9e022519c80cd137b9567d9a88a30fe"}