{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GI2RDMRRFZB6B55VLEY265PXSW","short_pith_number":"pith:GI2RDMRR","schema_version":"1.0","canonical_sha256":"323511b2312e43e0f7b55931af75f7959061930d87c62cbaed8e3e4e24ae4259","source":{"kind":"arxiv","id":"1802.09564","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrei Rusu, J\\'anos Kram\\'ar, Josh Merel, Nando de Freitas, Nicolas Heess, Raia Hadsell, Saran Tunyasuvunakool, Serkan Cabi, Tom Erez, Yuke Zhu, Ziyu Wang","submitted_at":"2018-02-26T19:25:25Z","abstract_excerpt":"We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation tasks and train end-to-end visuomotor policies that map directly from RGB camera inputs to joint velocities. We demonstrate that our approach can solve a wide variety of visuomotor tasks, for which engineering a scripted controller would be laborious. In experiments, our reinforcement and imitation agent achieves significantly better performances than agents trained with reinforcement learning or "},"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":"1802.09564","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-02-26T19:25:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"884622fe68dfa1add77f6410528a76347d6f70456fe191a3b095ea4b2ca8dae0","abstract_canon_sha256":"d78694b4812f27ea62ecab805c97497f1ef028f522848852d6fa891e787cc03d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:53.738299Z","signature_b64":"j/ZK5vPjxXt6lH+54UZ4behx8qi8VthfExAUUhc523gdr3Mtw7MabvFS+sJw3komMluve0iV2aj7snVNXA31AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"323511b2312e43e0f7b55931af75f7959061930d87c62cbaed8e3e4e24ae4259","last_reissued_at":"2026-05-18T00:14:53.737790Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:53.737790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Andrei Rusu, J\\'anos Kram\\'ar, Josh Merel, Nando de Freitas, Nicolas Heess, Raia Hadsell, Saran Tunyasuvunakool, Serkan Cabi, Tom Erez, Yuke Zhu, Ziyu Wang","submitted_at":"2018-02-26T19:25:25Z","abstract_excerpt":"We propose a model-free deep reinforcement learning method that leverages a small amount of demonstration data to assist a reinforcement learning agent. We apply this approach to robotic manipulation tasks and train end-to-end visuomotor policies that map directly from RGB camera inputs to joint velocities. We demonstrate that our approach can solve a wide variety of visuomotor tasks, for which engineering a scripted controller would be laborious. In experiments, our reinforcement and imitation agent achieves significantly better performances than agents trained with reinforcement learning or "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09564","kind":"arxiv","version":2},"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":"1802.09564","created_at":"2026-05-18T00:14:53.737867+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.09564v2","created_at":"2026-05-18T00:14:53.737867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09564","created_at":"2026-05-18T00:14:53.737867+00:00"},{"alias_kind":"pith_short_12","alias_value":"GI2RDMRRFZB6","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GI2RDMRRFZB6B55V","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GI2RDMRR","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":101,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":123,"is_internal_anchor":true},{"citing_arxiv_id":"2406.02523","citing_title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10165","citing_title":"MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW","json":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW.json","graph_json":"https://pith.science/api/pith-number/GI2RDMRRFZB6B55VLEY265PXSW/graph.json","events_json":"https://pith.science/api/pith-number/GI2RDMRRFZB6B55VLEY265PXSW/events.json","paper":"https://pith.science/paper/GI2RDMRR"},"agent_actions":{"view_html":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW","download_json":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW.json","view_paper":"https://pith.science/paper/GI2RDMRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.09564&json=true","fetch_graph":"https://pith.science/api/pith-number/GI2RDMRRFZB6B55VLEY265PXSW/graph.json","fetch_events":"https://pith.science/api/pith-number/GI2RDMRRFZB6B55VLEY265PXSW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW/action/storage_attestation","attest_author":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW/action/author_attestation","sign_citation":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW/action/citation_signature","submit_replication":"https://pith.science/pith/GI2RDMRRFZB6B55VLEY265PXSW/action/replication_record"}},"created_at":"2026-05-18T00:14:53.737867+00:00","updated_at":"2026-05-18T00:14:53.737867+00:00"}