{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DVYPS7AMFXA2TII3DD37VCSWN2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8deae585d3806fd2a89f744f66faa98b4464a17db062b24a9c7d6c9d5a262808","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-24T14:23:57Z","title_canon_sha256":"a2a3dde0af1e8c7688e5921df44ee57801c8dfd72273b38b985d8168019dfe3b"},"schema_version":"1.0","source":{"id":"2011.12105","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.12105","created_at":"2026-07-05T03:37:39Z"},{"alias_kind":"arxiv_version","alias_value":"2011.12105v3","created_at":"2026-07-05T03:37:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.12105","created_at":"2026-07-05T03:37:39Z"},{"alias_kind":"pith_short_12","alias_value":"DVYPS7AMFXA2","created_at":"2026-07-05T03:37:39Z"},{"alias_kind":"pith_short_16","alias_value":"DVYPS7AMFXA2TII3","created_at":"2026-07-05T03:37:39Z"},{"alias_kind":"pith_short_8","alias_value":"DVYPS7AM","created_at":"2026-07-05T03:37:39Z"}],"graph_snapshots":[{"event_id":"sha256:d6065ce8e3b560c642347302035f58d93974485664f9d7b6037e32e13c1566a7","target":"graph","created_at":"2026-07-05T03:37:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.12105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guangming Wang, Hesheng Wang, Minjian Xin, Wenhua Wu, Zhe Liu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-24T14:23:57Z","title":"Learning of Long-Horizon Sparse-Reward Robotic Manipulator Tasks with Base Controllers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.12105","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:db8a6fa59cc962290be6420f8981bdfadfce83c1ee63b346fe569a7820276cc9","target":"record","created_at":"2026-07-05T03:37:39Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8deae585d3806fd2a89f744f66faa98b4464a17db062b24a9c7d6c9d5a262808","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-24T14:23:57Z","title_canon_sha256":"a2a3dde0af1e8c7688e5921df44ee57801c8dfd72273b38b985d8168019dfe3b"},"schema_version":"1.0","source":{"id":"2011.12105","kind":"arxiv","version":3}},"canonical_sha256":"1d70f97c0c2dc1a9a11b18f7fa8a566e8ec63eb50962679f46357d503b3da6d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d70f97c0c2dc1a9a11b18f7fa8a566e8ec63eb50962679f46357d503b3da6d3","first_computed_at":"2026-07-05T03:37:39.500921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:39.500921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xKd6HkC32f2ze+Yn5X4FmpNI6YFEMUAKsY0iROsqW2TVRe6Sq2q+WLR/7ajYDtPRdufEgfHvJZrTOmG4ObKEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:39.501338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.12105","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db8a6fa59cc962290be6420f8981bdfadfce83c1ee63b346fe569a7820276cc9","sha256:d6065ce8e3b560c642347302035f58d93974485664f9d7b6037e32e13c1566a7"],"state_sha256":"b9bdbf139864bf027e0416c1d3e0a8766faeb236956b4b08f71f97f5d7db0c01"}