{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5WDEZPU32TIT7KEX6W4GFUMLQF","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":"75ff7e9470d7b9ed4f179cbcc497694e780f6fbd2f75606fe1cb778729bfa7fe","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-17T18:47:47Z","title_canon_sha256":"384e567df1cfbd9e862cc5561c8eeaf43f6a84737154cdd4324fe35b2c1340a3"},"schema_version":"1.0","source":{"id":"1809.06404","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.06404","created_at":"2026-05-17T23:52:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.06404v3","created_at":"2026-05-17T23:52:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06404","created_at":"2026-05-17T23:52:52Z"},{"alias_kind":"pith_short_12","alias_value":"5WDEZPU32TIT","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5WDEZPU32TIT7KEX","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5WDEZPU3","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:560c76dd088d02513be03bb1ea5a1a0151dd85a063cd294d20490b69ecc3721b","target":"graph","created_at":"2026-05-17T23:52:52Z","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"},"paper":{"abstract_excerpt":"We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy inverse reinforcement learning to learn near-optimal rewards and policies. Empowerment-based regularization prevents the policy from overfitting to expert demonstrations, which advantageously leads to more generalized behaviors that result in learning near-optimal rewards. Our method simultaneously learns empowerment through variational information maximizati","authors_text":"Ahmed H. Qureshi, Byron Boots, Michael C. Yip","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-17T18:47:47Z","title":"Adversarial Imitation via Variational Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06404","kind":"arxiv","version":3},"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":"sha256:30032497d91682bb63dcd7661db44fd693c91a6fefda13e5e7d79ddca632d64c","target":"record","created_at":"2026-05-17T23:52:52Z","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":"75ff7e9470d7b9ed4f179cbcc497694e780f6fbd2f75606fe1cb778729bfa7fe","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-17T18:47:47Z","title_canon_sha256":"384e567df1cfbd9e862cc5561c8eeaf43f6a84737154cdd4324fe35b2c1340a3"},"schema_version":"1.0","source":{"id":"1809.06404","kind":"arxiv","version":3}},"canonical_sha256":"ed864cbe9bd4d13fa897f5b862d18b8173d04722c513a37ebe98dfebdf9ab302","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed864cbe9bd4d13fa897f5b862d18b8173d04722c513a37ebe98dfebdf9ab302","first_computed_at":"2026-05-17T23:52:52.218489Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:52.218489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"abMgbzp7SEcdb6EZhiTPw2ZKfycBmHokff+REIR8knL+SpMWSUtWomYkzGBm80h2LQ4d9cqLr/3NuOA8UR9MDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:52.219233Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.06404","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30032497d91682bb63dcd7661db44fd693c91a6fefda13e5e7d79ddca632d64c","sha256:560c76dd088d02513be03bb1ea5a1a0151dd85a063cd294d20490b69ecc3721b"],"state_sha256":"ea1a01ae6c9d6ba2f1ac59701a6a74b0621f5a81cd0c4e6ce079054acad3c723"}