{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:X2OBTUN3FERCXRG4YEGWPLS32V","short_pith_number":"pith:X2OBTUN3","schema_version":"1.0","canonical_sha256":"be9c19d1bb29222bc4dcc10d67ae5bd57968e23dd0630be6c410ab052b56ccc1","source":{"kind":"arxiv","id":"1905.07866","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning without Ground-Truth State","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"David Held, Harjatin Singh Baweja, Xingyu Lin","submitted_at":"2019-05-20T04:17:03Z","abstract_excerpt":"To perform robot manipulation tasks, a low-dimensional state of the environment typically needs to be estimated. However, designing a state estimator can sometimes be difficult, especially in environments with deformable objects. An alternative is to learn an end-to-end policy that maps directly from high-dimensional sensor inputs to actions. However, if this policy is trained with reinforcement learning, then without a state estimator, it is hard to specify a reward function based on high-dimensional observations. To meet this challenge, we propose a simple indicator reward function for goal-"},"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":"1905.07866","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-05-20T04:17:03Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ed0da2336aaccc6050027fcde9cea23ddc0ee62175a4fb0f71239e69f7ba1c36","abstract_canon_sha256":"e8a5df416aff4d003a1f0863abe81ea5dad2567275249a349b7097723ca79e73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:38.746617Z","signature_b64":"bZDFqR3+rlb2r3zuRJhCGSUCoJykyh/nGHTJSwOv7ugGrt5YxdtpqxZ+5Kw5UDT5BLl99bdQzMDu11vPca+pDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be9c19d1bb29222bc4dcc10d67ae5bd57968e23dd0630be6c410ab052b56ccc1","last_reissued_at":"2026-05-17T23:40:38.745630Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:38.745630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning without Ground-Truth State","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"David Held, Harjatin Singh Baweja, Xingyu Lin","submitted_at":"2019-05-20T04:17:03Z","abstract_excerpt":"To perform robot manipulation tasks, a low-dimensional state of the environment typically needs to be estimated. However, designing a state estimator can sometimes be difficult, especially in environments with deformable objects. An alternative is to learn an end-to-end policy that maps directly from high-dimensional sensor inputs to actions. However, if this policy is trained with reinforcement learning, then without a state estimator, it is hard to specify a reward function based on high-dimensional observations. To meet this challenge, we propose a simple indicator reward function for goal-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07866","kind":"arxiv","version":2},"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":"1905.07866","created_at":"2026-05-17T23:40:38.745710+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.07866v2","created_at":"2026-05-17T23:40:38.745710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07866","created_at":"2026-05-17T23:40:38.745710+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2OBTUN3FERC","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2OBTUN3FERCXRG4","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2OBTUN3","created_at":"2026-05-18T12:33:33.725879+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/X2OBTUN3FERCXRG4YEGWPLS32V","json":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V.json","graph_json":"https://pith.science/api/pith-number/X2OBTUN3FERCXRG4YEGWPLS32V/graph.json","events_json":"https://pith.science/api/pith-number/X2OBTUN3FERCXRG4YEGWPLS32V/events.json","paper":"https://pith.science/paper/X2OBTUN3"},"agent_actions":{"view_html":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V","download_json":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V.json","view_paper":"https://pith.science/paper/X2OBTUN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.07866&json=true","fetch_graph":"https://pith.science/api/pith-number/X2OBTUN3FERCXRG4YEGWPLS32V/graph.json","fetch_events":"https://pith.science/api/pith-number/X2OBTUN3FERCXRG4YEGWPLS32V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V/action/storage_attestation","attest_author":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V/action/author_attestation","sign_citation":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V/action/citation_signature","submit_replication":"https://pith.science/pith/X2OBTUN3FERCXRG4YEGWPLS32V/action/replication_record"}},"created_at":"2026-05-17T23:40:38.745710+00:00","updated_at":"2026-05-17T23:40:38.745710+00:00"}