{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JWT5XBCBBJZJASDR2PFT46RVGK","short_pith_number":"pith:JWT5XBCB","schema_version":"1.0","canonical_sha256":"4da7db84410a72904871d3cb3e7a3532b46691a8cacb532202161f8a7f97a5a0","source":{"kind":"arxiv","id":"2002.11879","version":1},"attestation_state":"computed","paper":{"title":"State-only Imitation with Transition Dynamics Mismatch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jian Peng, Tanmay Gangwani","submitted_at":"2020-02-27T02:27:46Z","abstract_excerpt":"Imitation Learning (IL) is a popular paradigm for training agents to achieve complicated goals by leveraging expert behavior, rather than dealing with the hardships of designing a correct reward function. With the environment modeled as a Markov Decision Process (MDP), most of the existing IL algorithms are contingent on the availability of expert demonstrations in the same MDP as the one in which a new imitator policy is to be learned. This is uncharacteristic of many real-life scenarios where discrepancies between the expert and the imitator MDPs are common, especially in the transition dyna"},"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":"2002.11879","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-27T02:27:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"daa5b87b9ec8eed67add82579d096a54ca171d6ca1b4ea2fa6917758adfb0477","abstract_canon_sha256":"c7adaef99243021bc6018a611625a533d6974a6d310235d126de1c479f739090"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:09.860475Z","signature_b64":"RZRT8r2EUXPrps5iqVt78wpL9gY7zPpKHu44yCmVv5laLGS2oHEtY7x0pD+gsM7m6szCkgNPJHcZjPKOdreBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4da7db84410a72904871d3cb3e7a3532b46691a8cacb532202161f8a7f97a5a0","last_reissued_at":"2026-07-05T00:44:09.860034Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:09.860034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"State-only Imitation with Transition Dynamics Mismatch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jian Peng, Tanmay Gangwani","submitted_at":"2020-02-27T02:27:46Z","abstract_excerpt":"Imitation Learning (IL) is a popular paradigm for training agents to achieve complicated goals by leveraging expert behavior, rather than dealing with the hardships of designing a correct reward function. With the environment modeled as a Markov Decision Process (MDP), most of the existing IL algorithms are contingent on the availability of expert demonstrations in the same MDP as the one in which a new imitator policy is to be learned. This is uncharacteristic of many real-life scenarios where discrepancies between the expert and the imitator MDPs are common, especially in the transition dyna"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11879","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.11879/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2002.11879","created_at":"2026-07-05T00:44:09.860092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.11879v1","created_at":"2026-07-05T00:44:09.860092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11879","created_at":"2026-07-05T00:44:09.860092+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWT5XBCBBJZJ","created_at":"2026-07-05T00:44:09.860092+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWT5XBCBBJZJASDR","created_at":"2026-07-05T00:44:09.860092+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWT5XBCB","created_at":"2026-07-05T00:44:09.860092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09183","citing_title":"Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09183","citing_title":"Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JWT5XBCBBJZJASDR2PFT46RVGK","json":"https://pith.science/pith/JWT5XBCBBJZJASDR2PFT46RVGK.json","graph_json":"https://pith.science/api/pith-number/JWT5XBCBBJZJASDR2PFT46RVGK/graph.json","events_json":"https://pith.science/api/pith-number/JWT5XBCBBJZJASDR2PFT46RVGK/events.json","paper":"https://pith.science/paper/JWT5XBCB"},"agent_actions":{"view_html":"https://pith.science/pith/JWT5XBCBBJZJASDR2PFT46RVGK","download_json":"https://pith.science/pith/JWT5XBCBBJZJASDR2PFT46RVGK.json","view_paper":"https://pith.science/paper/JWT5XBCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.11879&json=true","fetch_graph":"https://pith.science/api/pith-number/JWT5XBCBBJZJASDR2PFT46RVGK/graph.json","fetch_events":"https://pith.science/api/pith-number/JWT5XBCBBJZJASDR2PFT46RVGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWT5XBCBBJZJASDR2PFT46RVGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWT5XBCBBJZJASDR2PFT46RVGK/action/storage_attestation","attest_author":"https://pith.science/pith/JWT5XBCBBJZJASDR2PFT46RVGK/action/author_attestation","sign_citation":"https://pith.science/pith/JWT5XBCBBJZJASDR2PFT46RVGK/action/citation_signature","submit_replication":"https://pith.science/pith/JWT5XBCBBJZJASDR2PFT46RVGK/action/replication_record"}},"created_at":"2026-07-05T00:44:09.860092+00:00","updated_at":"2026-07-05T00:44:09.860092+00:00"}