{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DVYPS7AMFXA2TII3DD37VCSWN2","short_pith_number":"pith:DVYPS7AM","schema_version":"1.0","canonical_sha256":"1d70f97c0c2dc1a9a11b18f7fa8a566e8ec63eb50962679f46357d503b3da6d3","source":{"kind":"arxiv","id":"2011.12105","version":3},"attestation_state":"computed","paper":{"title":"Learning of Long-Horizon Sparse-Reward Robotic Manipulator Tasks with Base Controllers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Guangming Wang, Hesheng Wang, Minjian Xin, Wenhua Wu, Zhe Liu","submitted_at":"2020-11-24T14:23:57Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end. However, there are still many challenges for long-horizon sparse-reward robotic manipulator tasks. On the one hand, a sparse-reward setting causes exploration inefficient. On the other hand, exploration using physical robots is of high cost and unsafe. In this paper, we propose a method of learning long-horizon sparse-reward tasks utilizing one or more existing traditional controllers named base controllers in this paper. Built upon Deep Deterministic Policy Gradients (DDPG), our algorithm incorporat"},"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":"2011.12105","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-24T14:23:57Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a2a3dde0af1e8c7688e5921df44ee57801c8dfd72273b38b985d8168019dfe3b","abstract_canon_sha256":"8deae585d3806fd2a89f744f66faa98b4464a17db062b24a9c7d6c9d5a262808"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:37:39.501338Z","signature_b64":"xKd6HkC32f2ze+Yn5X4FmpNI6YFEMUAKsY0iROsqW2TVRe6Sq2q+WLR/7ajYDtPRdufEgfHvJZrTOmG4ObKEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d70f97c0c2dc1a9a11b18f7fa8a566e8ec63eb50962679f46357d503b3da6d3","last_reissued_at":"2026-07-05T03:37:39.500921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:37:39.500921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning of Long-Horizon Sparse-Reward Robotic Manipulator Tasks with Base Controllers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Guangming Wang, Hesheng Wang, Minjian Xin, Wenhua Wu, Zhe Liu","submitted_at":"2020-11-24T14:23:57Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) enables robots to perform some intelligent tasks end-to-end. However, there are still many challenges for long-horizon sparse-reward robotic manipulator tasks. On the one hand, a sparse-reward setting causes exploration inefficient. On the other hand, exploration using physical robots is of high cost and unsafe. In this paper, we propose a method of learning long-horizon sparse-reward tasks utilizing one or more existing traditional controllers named base controllers in this paper. Built upon Deep Deterministic Policy Gradients (DDPG), our algorithm incorporat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.12105","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/2011.12105/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":"2011.12105","created_at":"2026-07-05T03:37:39.500976+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.12105v3","created_at":"2026-07-05T03:37:39.500976+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.12105","created_at":"2026-07-05T03:37:39.500976+00:00"},{"alias_kind":"pith_short_12","alias_value":"DVYPS7AMFXA2","created_at":"2026-07-05T03:37:39.500976+00:00"},{"alias_kind":"pith_short_16","alias_value":"DVYPS7AMFXA2TII3","created_at":"2026-07-05T03:37:39.500976+00:00"},{"alias_kind":"pith_short_8","alias_value":"DVYPS7AM","created_at":"2026-07-05T03:37:39.500976+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/DVYPS7AMFXA2TII3DD37VCSWN2","json":"https://pith.science/pith/DVYPS7AMFXA2TII3DD37VCSWN2.json","graph_json":"https://pith.science/api/pith-number/DVYPS7AMFXA2TII3DD37VCSWN2/graph.json","events_json":"https://pith.science/api/pith-number/DVYPS7AMFXA2TII3DD37VCSWN2/events.json","paper":"https://pith.science/paper/DVYPS7AM"},"agent_actions":{"view_html":"https://pith.science/pith/DVYPS7AMFXA2TII3DD37VCSWN2","download_json":"https://pith.science/pith/DVYPS7AMFXA2TII3DD37VCSWN2.json","view_paper":"https://pith.science/paper/DVYPS7AM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.12105&json=true","fetch_graph":"https://pith.science/api/pith-number/DVYPS7AMFXA2TII3DD37VCSWN2/graph.json","fetch_events":"https://pith.science/api/pith-number/DVYPS7AMFXA2TII3DD37VCSWN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DVYPS7AMFXA2TII3DD37VCSWN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DVYPS7AMFXA2TII3DD37VCSWN2/action/storage_attestation","attest_author":"https://pith.science/pith/DVYPS7AMFXA2TII3DD37VCSWN2/action/author_attestation","sign_citation":"https://pith.science/pith/DVYPS7AMFXA2TII3DD37VCSWN2/action/citation_signature","submit_replication":"https://pith.science/pith/DVYPS7AMFXA2TII3DD37VCSWN2/action/replication_record"}},"created_at":"2026-07-05T03:37:39.500976+00:00","updated_at":"2026-07-05T03:37:39.500976+00:00"}