{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WVUADCQI5TERUIXV5IZR5T44AX","short_pith_number":"pith:WVUADCQI","schema_version":"1.0","canonical_sha256":"b568018a08ecc91a22f5ea331ecf9c05de27c00baa306d9867bf2b691c70af6e","source":{"kind":"arxiv","id":"1905.06274","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Robotics and Control with Active Uncertainty Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Narendra Patwardhan, Zequn Wang","submitted_at":"2019-05-15T16:21:05Z","abstract_excerpt":"Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in robotics due to safety and time consumption. Model-based methods such as PILCO or BlackDrops, while data-efficient, provide solutions with limited robustness and complexity. To address this tradeoff, we introduce active uncertainty reduction-based virtual environments, which are formed through limited trials conducted in the original environment. We provide a"},"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":"1905.06274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T16:21:05Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"bc6ed150467f4798504046b6b5c81b31ca051da85a5ee171464971453723652c","abstract_canon_sha256":"342763bf6eb480db4ddc4feb7412747cef25fb28f54acaba228adf40eeaa6979"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:06.991354Z","signature_b64":"cPK8ET/Xxv9TuGT2QU5T+pvX74Q5pin1UGdFboqSvHptsCHyw+1MDaNEzLFk+85q7qfad6J6r+7aUhrjcCBVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b568018a08ecc91a22f5ea331ecf9c05de27c00baa306d9867bf2b691c70af6e","last_reissued_at":"2026-05-17T23:46:06.990439Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:06.990439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Robotics and Control with Active Uncertainty Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Narendra Patwardhan, Zequn Wang","submitted_at":"2019-05-15T16:21:05Z","abstract_excerpt":"Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in robotics due to safety and time consumption. Model-based methods such as PILCO or BlackDrops, while data-efficient, provide solutions with limited robustness and complexity. To address this tradeoff, we introduce active uncertainty reduction-based virtual environments, which are formed through limited trials conducted in the original environment. We provide a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06274","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":"1905.06274","created_at":"2026-05-17T23:46:06.990521+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.06274v1","created_at":"2026-05-17T23:46:06.990521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06274","created_at":"2026-05-17T23:46:06.990521+00:00"},{"alias_kind":"pith_short_12","alias_value":"WVUADCQI5TER","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"WVUADCQI5TERUIXV","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"WVUADCQI","created_at":"2026-05-18T12:33:33.725879+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/WVUADCQI5TERUIXV5IZR5T44AX","json":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX.json","graph_json":"https://pith.science/api/pith-number/WVUADCQI5TERUIXV5IZR5T44AX/graph.json","events_json":"https://pith.science/api/pith-number/WVUADCQI5TERUIXV5IZR5T44AX/events.json","paper":"https://pith.science/paper/WVUADCQI"},"agent_actions":{"view_html":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX","download_json":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX.json","view_paper":"https://pith.science/paper/WVUADCQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.06274&json=true","fetch_graph":"https://pith.science/api/pith-number/WVUADCQI5TERUIXV5IZR5T44AX/graph.json","fetch_events":"https://pith.science/api/pith-number/WVUADCQI5TERUIXV5IZR5T44AX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX/action/storage_attestation","attest_author":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX/action/author_attestation","sign_citation":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX/action/citation_signature","submit_replication":"https://pith.science/pith/WVUADCQI5TERUIXV5IZR5T44AX/action/replication_record"}},"created_at":"2026-05-17T23:46:06.990521+00:00","updated_at":"2026-05-17T23:46:06.990521+00:00"}