{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5WDEZPU32TIT7KEX6W4GFUMLQF","short_pith_number":"pith:5WDEZPU3","schema_version":"1.0","canonical_sha256":"ed864cbe9bd4d13fa897f5b862d18b8173d04722c513a37ebe98dfebdf9ab302","source":{"kind":"arxiv","id":"1809.06404","version":3},"attestation_state":"computed","paper":{"title":"Adversarial Imitation via Variational Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed H. Qureshi, Byron Boots, Michael C. Yip","submitted_at":"2018-09-17T18:47:47Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1809.06404","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-17T18:47:47Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"384e567df1cfbd9e862cc5561c8eeaf43f6a84737154cdd4324fe35b2c1340a3","abstract_canon_sha256":"75ff7e9470d7b9ed4f179cbcc497694e780f6fbd2f75606fe1cb778729bfa7fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:52.219233Z","signature_b64":"abMgbzp7SEcdb6EZhiTPw2ZKfycBmHokff+REIR8knL+SpMWSUtWomYkzGBm80h2LQ4d9cqLr/3NuOA8UR9MDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed864cbe9bd4d13fa897f5b862d18b8173d04722c513a37ebe98dfebdf9ab302","last_reissued_at":"2026-05-17T23:52:52.218489Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:52.218489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Imitation via Variational Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed H. Qureshi, Byron Boots, Michael C. Yip","submitted_at":"2018-09-17T18:47:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06404","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1809.06404","created_at":"2026-05-17T23:52:52.218614+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.06404v3","created_at":"2026-05-17T23:52:52.218614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06404","created_at":"2026-05-17T23:52:52.218614+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WDEZPU32TIT","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WDEZPU32TIT7KEX","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WDEZPU3","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WDEZPU32TIT7KEX6W4GFUMLQF","json":"https://pith.science/pith/5WDEZPU32TIT7KEX6W4GFUMLQF.json","graph_json":"https://pith.science/api/pith-number/5WDEZPU32TIT7KEX6W4GFUMLQF/graph.json","events_json":"https://pith.science/api/pith-number/5WDEZPU32TIT7KEX6W4GFUMLQF/events.json","paper":"https://pith.science/paper/5WDEZPU3"},"agent_actions":{"view_html":"https://pith.science/pith/5WDEZPU32TIT7KEX6W4GFUMLQF","download_json":"https://pith.science/pith/5WDEZPU32TIT7KEX6W4GFUMLQF.json","view_paper":"https://pith.science/paper/5WDEZPU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.06404&json=true","fetch_graph":"https://pith.science/api/pith-number/5WDEZPU32TIT7KEX6W4GFUMLQF/graph.json","fetch_events":"https://pith.science/api/pith-number/5WDEZPU32TIT7KEX6W4GFUMLQF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WDEZPU32TIT7KEX6W4GFUMLQF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WDEZPU32TIT7KEX6W4GFUMLQF/action/storage_attestation","attest_author":"https://pith.science/pith/5WDEZPU32TIT7KEX6W4GFUMLQF/action/author_attestation","sign_citation":"https://pith.science/pith/5WDEZPU32TIT7KEX6W4GFUMLQF/action/citation_signature","submit_replication":"https://pith.science/pith/5WDEZPU32TIT7KEX6W4GFUMLQF/action/replication_record"}},"created_at":"2026-05-17T23:52:52.218614+00:00","updated_at":"2026-05-17T23:52:52.218614+00:00"}