{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ETXISJABNBG7AJZH6IG2NLSJQ2","short_pith_number":"pith:ETXISJAB","schema_version":"1.0","canonical_sha256":"24ee892401684df02727f20da6ae4986983ed74beb34ecc894c9d2968f19741d","source":{"kind":"arxiv","id":"1710.10116","version":1},"attestation_state":"computed","paper":{"title":"Inverse Reinforcement Learning Under Noisy Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Prashant Doshi, Shervin Shahryari","submitted_at":"2017-10-27T13:10:26Z","abstract_excerpt":"We consider the problem of performing inverse reinforcement learning when the trajectory of the expert is not perfectly observed by the learner. Instead, a noisy continuous-time observation of the trajectory is provided to the learner. This problem exhibits wide-ranging applications and the specific application we consider here is the scenario in which the learner seeks to penetrate a perimeter patrolled by a robot. The learner's field of view is limited due to which it cannot observe the patroller's complete trajectory. Instead, we allow the learner to listen to the expert's movement sound, w"},"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":"1710.10116","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-10-27T13:10:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fb3aa150f41ce7cdf332541423c930c5f581822e4b195f72be1eef0fb3c37710","abstract_canon_sha256":"9dd4e71972a65399a3e6cc9bea833c1dbce50c3e8516c0d80dcd9c4c5ed970a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:54.726192Z","signature_b64":"JaQm/d9uPG+DdJoNUtGeTubz58dLrzQPu0x0TwwANcSSDb39Yts4pM/u0yeqAsskq0PYwBzULOOX7bv/cUBYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24ee892401684df02727f20da6ae4986983ed74beb34ecc894c9d2968f19741d","last_reissued_at":"2026-05-18T00:31:54.725585Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:54.725585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inverse Reinforcement Learning Under Noisy Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Prashant Doshi, Shervin Shahryari","submitted_at":"2017-10-27T13:10:26Z","abstract_excerpt":"We consider the problem of performing inverse reinforcement learning when the trajectory of the expert is not perfectly observed by the learner. Instead, a noisy continuous-time observation of the trajectory is provided to the learner. This problem exhibits wide-ranging applications and the specific application we consider here is the scenario in which the learner seeks to penetrate a perimeter patrolled by a robot. The learner's field of view is limited due to which it cannot observe the patroller's complete trajectory. Instead, we allow the learner to listen to the expert's movement sound, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10116","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":""},"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":"1710.10116","created_at":"2026-05-18T00:31:54.725703+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.10116v1","created_at":"2026-05-18T00:31:54.725703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10116","created_at":"2026-05-18T00:31:54.725703+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETXISJABNBG7","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETXISJABNBG7AJZH","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETXISJAB","created_at":"2026-05-18T12:31:12.930513+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/ETXISJABNBG7AJZH6IG2NLSJQ2","json":"https://pith.science/pith/ETXISJABNBG7AJZH6IG2NLSJQ2.json","graph_json":"https://pith.science/api/pith-number/ETXISJABNBG7AJZH6IG2NLSJQ2/graph.json","events_json":"https://pith.science/api/pith-number/ETXISJABNBG7AJZH6IG2NLSJQ2/events.json","paper":"https://pith.science/paper/ETXISJAB"},"agent_actions":{"view_html":"https://pith.science/pith/ETXISJABNBG7AJZH6IG2NLSJQ2","download_json":"https://pith.science/pith/ETXISJABNBG7AJZH6IG2NLSJQ2.json","view_paper":"https://pith.science/paper/ETXISJAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.10116&json=true","fetch_graph":"https://pith.science/api/pith-number/ETXISJABNBG7AJZH6IG2NLSJQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/ETXISJABNBG7AJZH6IG2NLSJQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETXISJABNBG7AJZH6IG2NLSJQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETXISJABNBG7AJZH6IG2NLSJQ2/action/storage_attestation","attest_author":"https://pith.science/pith/ETXISJABNBG7AJZH6IG2NLSJQ2/action/author_attestation","sign_citation":"https://pith.science/pith/ETXISJABNBG7AJZH6IG2NLSJQ2/action/citation_signature","submit_replication":"https://pith.science/pith/ETXISJABNBG7AJZH6IG2NLSJQ2/action/replication_record"}},"created_at":"2026-05-18T00:31:54.725703+00:00","updated_at":"2026-05-18T00:31:54.725703+00:00"}