{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WJIRRSXILHCUYZWYWQMVDFAQB4","short_pith_number":"pith:WJIRRSXI","schema_version":"1.0","canonical_sha256":"b25118cae859c54c66d8b4195194100f1374d3d3fb5d2638c334bb7db480b43b","source":{"kind":"arxiv","id":"2104.12842","version":1},"attestation_state":"computed","paper":{"title":"End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Christopher Amato, Deniz Erdogmus, Mohammadreza Sharif, Taskin Padir","submitted_at":"2021-04-26T19:39:23Z","abstract_excerpt":"State-of-the-art human-in-the-loop robot grasping is hugely suffered by Electromyography (EMG) inference robustness issues. As a workaround, researchers have been looking into integrating EMG with other signals, often in an ad hoc manner. In this paper, we are presenting a method for end-to-end training of a policy for human-in-the-loop robot grasping on real reaching trajectories. For this purpose we use Reinforcement Learning (RL) and Imitation Learning (IL) in DEXTRON (DEXTerity enviRONment), a stochastic simulation environment with real human trajectories that are augmented and selected us"},"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":"2104.12842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2021-04-26T19:39:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2a13403c788f73d1dbb668ba7a532f08493182615859992505690950fa668674","abstract_canon_sha256":"7197e32d99afb600007875e2c8651505685fa398dc4b5e5ae6fcfca3491cb88f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:13.678190Z","signature_b64":"Ztr9vQMyq+z88Ouxc8wJX6Ywpifs1uX6G51QUvFw8z8KhRMUksjUrxwriNKo60wkJBANX7W1RqmSRZbOlMWsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b25118cae859c54c66d8b4195194100f1374d3d3fb5d2638c334bb7db480b43b","last_reissued_at":"2026-07-05T03:25:13.677617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:13.677617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Christopher Amato, Deniz Erdogmus, Mohammadreza Sharif, Taskin Padir","submitted_at":"2021-04-26T19:39:23Z","abstract_excerpt":"State-of-the-art human-in-the-loop robot grasping is hugely suffered by Electromyography (EMG) inference robustness issues. As a workaround, researchers have been looking into integrating EMG with other signals, often in an ad hoc manner. In this paper, we are presenting a method for end-to-end training of a policy for human-in-the-loop robot grasping on real reaching trajectories. For this purpose we use Reinforcement Learning (RL) and Imitation Learning (IL) in DEXTRON (DEXTerity enviRONment), a stochastic simulation environment with real human trajectories that are augmented and selected us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.12842","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/2104.12842/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":"2104.12842","created_at":"2026-07-05T03:25:13.677709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.12842v1","created_at":"2026-07-05T03:25:13.677709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.12842","created_at":"2026-07-05T03:25:13.677709+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJIRRSXILHCU","created_at":"2026-07-05T03:25:13.677709+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJIRRSXILHCUYZWY","created_at":"2026-07-05T03:25:13.677709+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJIRRSXI","created_at":"2026-07-05T03:25:13.677709+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/WJIRRSXILHCUYZWYWQMVDFAQB4","json":"https://pith.science/pith/WJIRRSXILHCUYZWYWQMVDFAQB4.json","graph_json":"https://pith.science/api/pith-number/WJIRRSXILHCUYZWYWQMVDFAQB4/graph.json","events_json":"https://pith.science/api/pith-number/WJIRRSXILHCUYZWYWQMVDFAQB4/events.json","paper":"https://pith.science/paper/WJIRRSXI"},"agent_actions":{"view_html":"https://pith.science/pith/WJIRRSXILHCUYZWYWQMVDFAQB4","download_json":"https://pith.science/pith/WJIRRSXILHCUYZWYWQMVDFAQB4.json","view_paper":"https://pith.science/paper/WJIRRSXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.12842&json=true","fetch_graph":"https://pith.science/api/pith-number/WJIRRSXILHCUYZWYWQMVDFAQB4/graph.json","fetch_events":"https://pith.science/api/pith-number/WJIRRSXILHCUYZWYWQMVDFAQB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJIRRSXILHCUYZWYWQMVDFAQB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJIRRSXILHCUYZWYWQMVDFAQB4/action/storage_attestation","attest_author":"https://pith.science/pith/WJIRRSXILHCUYZWYWQMVDFAQB4/action/author_attestation","sign_citation":"https://pith.science/pith/WJIRRSXILHCUYZWYWQMVDFAQB4/action/citation_signature","submit_replication":"https://pith.science/pith/WJIRRSXILHCUYZWYWQMVDFAQB4/action/replication_record"}},"created_at":"2026-07-05T03:25:13.677709+00:00","updated_at":"2026-07-05T03:25:13.677709+00:00"}