{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:G7PQ5PA3BSPWZMT5K55TMCDFYP","short_pith_number":"pith:G7PQ5PA3","schema_version":"1.0","canonical_sha256":"37df0ebc1b0c9f6cb27d577b360865c3f9efc39b391ec667bd7bc8460d199637","source":{"kind":"arxiv","id":"2109.15233","version":3},"attestation_state":"computed","paper":{"title":"Solving the Real Robot Challenge using Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"David Cordova Bulens, Francisco Roldan Sanchez, Kevin McGuinness, Noel O'Connor, Qiang Wang, Robert McCarthy, Stephen J. Redmond","submitted_at":"2021-09-30T16:12:17Z","abstract_excerpt":"This paper details our winning submission to Phase 1 of the 2021 Real Robot Challenge; a challenge in which a three-fingered robot must carry a cube along specified goal trajectories. To solve Phase 1, we use a pure reinforcement learning approach which requires minimal expert knowledge of the robotic system, or of robotic grasping in general. A sparse, goal-based reward is employed in conjunction with Hindsight Experience Replay to teach the control policy to move the cube to the desired x and y coordinates of the goal. Simultaneously, a dense distance-based reward is employed to teach the po"},"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":"2109.15233","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-30T16:12:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"74157e6b65562a99acb189fe1b5d82534e6ce9856460dfd8e792e3af8d06b956","abstract_canon_sha256":"aedd924d54703596891967c31310a4c9adb20079f22e66c313f8638018dc9076"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:09.430307Z","signature_b64":"duCqXVhMEdl7EWcFjad8upMcvGWNbDaW8aDb2qt8EvLh5/uhVGiYkAXf0eEywb/kjEoL833W5HWbAGEY5arWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37df0ebc1b0c9f6cb27d577b360865c3f9efc39b391ec667bd7bc8460d199637","last_reissued_at":"2026-07-05T04:35:09.429824Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:09.429824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving the Real Robot Challenge using Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"David Cordova Bulens, Francisco Roldan Sanchez, Kevin McGuinness, Noel O'Connor, Qiang Wang, Robert McCarthy, Stephen J. Redmond","submitted_at":"2021-09-30T16:12:17Z","abstract_excerpt":"This paper details our winning submission to Phase 1 of the 2021 Real Robot Challenge; a challenge in which a three-fingered robot must carry a cube along specified goal trajectories. To solve Phase 1, we use a pure reinforcement learning approach which requires minimal expert knowledge of the robotic system, or of robotic grasping in general. A sparse, goal-based reward is employed in conjunction with Hindsight Experience Replay to teach the control policy to move the cube to the desired x and y coordinates of the goal. Simultaneously, a dense distance-based reward is employed to teach the po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.15233","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.15233/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":"2109.15233","created_at":"2026-07-05T04:35:09.429883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.15233v3","created_at":"2026-07-05T04:35:09.429883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.15233","created_at":"2026-07-05T04:35:09.429883+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7PQ5PA3BSPW","created_at":"2026-07-05T04:35:09.429883+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7PQ5PA3BSPWZMT5","created_at":"2026-07-05T04:35:09.429883+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7PQ5PA3","created_at":"2026-07-05T04:35:09.429883+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/G7PQ5PA3BSPWZMT5K55TMCDFYP","json":"https://pith.science/pith/G7PQ5PA3BSPWZMT5K55TMCDFYP.json","graph_json":"https://pith.science/api/pith-number/G7PQ5PA3BSPWZMT5K55TMCDFYP/graph.json","events_json":"https://pith.science/api/pith-number/G7PQ5PA3BSPWZMT5K55TMCDFYP/events.json","paper":"https://pith.science/paper/G7PQ5PA3"},"agent_actions":{"view_html":"https://pith.science/pith/G7PQ5PA3BSPWZMT5K55TMCDFYP","download_json":"https://pith.science/pith/G7PQ5PA3BSPWZMT5K55TMCDFYP.json","view_paper":"https://pith.science/paper/G7PQ5PA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.15233&json=true","fetch_graph":"https://pith.science/api/pith-number/G7PQ5PA3BSPWZMT5K55TMCDFYP/graph.json","fetch_events":"https://pith.science/api/pith-number/G7PQ5PA3BSPWZMT5K55TMCDFYP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7PQ5PA3BSPWZMT5K55TMCDFYP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7PQ5PA3BSPWZMT5K55TMCDFYP/action/storage_attestation","attest_author":"https://pith.science/pith/G7PQ5PA3BSPWZMT5K55TMCDFYP/action/author_attestation","sign_citation":"https://pith.science/pith/G7PQ5PA3BSPWZMT5K55TMCDFYP/action/citation_signature","submit_replication":"https://pith.science/pith/G7PQ5PA3BSPWZMT5K55TMCDFYP/action/replication_record"}},"created_at":"2026-07-05T04:35:09.429883+00:00","updated_at":"2026-07-05T04:35:09.429883+00:00"}