{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:KD6BBJIUDB2L2RH3Z6U7I5DALF","short_pith_number":"pith:KD6BBJIU","schema_version":"1.0","canonical_sha256":"50fc10a5141874bd44fbcfa9f4746059556ee8cc3430ac394550f2c43d876393","source":{"kind":"arxiv","id":"1803.07067","version":1},"attestation_state":"computed","paper":{"title":"Setting up a Reinforcement Learning Task with a Real-World Robot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Brent J. Komer, Dmytro Korenkevych, James Bergstra","submitted_at":"2018-03-19T17:59:05Z","abstract_excerpt":"Reinforcement learning is a promising approach to developing hard-to-engineer adaptive solutions for complex and diverse robotic tasks. However, learning with real-world robots is often unreliable and difficult, which resulted in their low adoption in reinforcement learning research. This difficulty is worsened by the lack of guidelines for setting up learning tasks with robots. In this work, we develop a learning task with a UR5 robotic arm to bring to light some key elements of a task setup and study their contributions to the challenges with robots. We find that learning performance can be "},"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":"1803.07067","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-19T17:59:05Z","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"title_canon_sha256":"1a9ce6c02d9890390ca4d465fa28bd128cbbe7fa085924471fcd24b9a7bbfee4","abstract_canon_sha256":"29d24f32fccaa71db741c7b5857b81eadf0ba925d84ab1391a8613e713dbd15a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:40.419663Z","signature_b64":"b57iphk04xnXIRGH9J6luFUqRyIaPY4tQ3gyY/vx51Su0gugZjTBS6s/wdf86CrcbjZm3GcnAcnN1dLJTAYrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50fc10a5141874bd44fbcfa9f4746059556ee8cc3430ac394550f2c43d876393","last_reissued_at":"2026-05-18T00:20:40.418965Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:40.418965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Setting up a Reinforcement Learning Task with a Real-World Robot","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"A. Rupam Mahmood, Brent J. Komer, Dmytro Korenkevych, James Bergstra","submitted_at":"2018-03-19T17:59:05Z","abstract_excerpt":"Reinforcement learning is a promising approach to developing hard-to-engineer adaptive solutions for complex and diverse robotic tasks. However, learning with real-world robots is often unreliable and difficult, which resulted in their low adoption in reinforcement learning research. This difficulty is worsened by the lack of guidelines for setting up learning tasks with robots. In this work, we develop a learning task with a UR5 robotic arm to bring to light some key elements of a task setup and study their contributions to the challenges with robots. We find that learning performance can be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07067","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":"1803.07067","created_at":"2026-05-18T00:20:40.419075+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.07067v1","created_at":"2026-05-18T00:20:40.419075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07067","created_at":"2026-05-18T00:20:40.419075+00:00"},{"alias_kind":"pith_short_12","alias_value":"KD6BBJIUDB2L","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"KD6BBJIUDB2L2RH3","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"KD6BBJIU","created_at":"2026-05-18T12:32:33.847187+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/KD6BBJIUDB2L2RH3Z6U7I5DALF","json":"https://pith.science/pith/KD6BBJIUDB2L2RH3Z6U7I5DALF.json","graph_json":"https://pith.science/api/pith-number/KD6BBJIUDB2L2RH3Z6U7I5DALF/graph.json","events_json":"https://pith.science/api/pith-number/KD6BBJIUDB2L2RH3Z6U7I5DALF/events.json","paper":"https://pith.science/paper/KD6BBJIU"},"agent_actions":{"view_html":"https://pith.science/pith/KD6BBJIUDB2L2RH3Z6U7I5DALF","download_json":"https://pith.science/pith/KD6BBJIUDB2L2RH3Z6U7I5DALF.json","view_paper":"https://pith.science/paper/KD6BBJIU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.07067&json=true","fetch_graph":"https://pith.science/api/pith-number/KD6BBJIUDB2L2RH3Z6U7I5DALF/graph.json","fetch_events":"https://pith.science/api/pith-number/KD6BBJIUDB2L2RH3Z6U7I5DALF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KD6BBJIUDB2L2RH3Z6U7I5DALF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KD6BBJIUDB2L2RH3Z6U7I5DALF/action/storage_attestation","attest_author":"https://pith.science/pith/KD6BBJIUDB2L2RH3Z6U7I5DALF/action/author_attestation","sign_citation":"https://pith.science/pith/KD6BBJIUDB2L2RH3Z6U7I5DALF/action/citation_signature","submit_replication":"https://pith.science/pith/KD6BBJIUDB2L2RH3Z6U7I5DALF/action/replication_record"}},"created_at":"2026-05-18T00:20:40.419075+00:00","updated_at":"2026-05-18T00:20:40.419075+00:00"}