{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:B6YZUZGPS5LV4YPV4FWXOISFNG","short_pith_number":"pith:B6YZUZGP","schema_version":"1.0","canonical_sha256":"0fb19a64cf97575e61f5e16d7722456996d96ea4b3ef881386818fd31191c69a","source":{"kind":"arxiv","id":"1504.00702","version":5},"attestation_state":"computed","paper":{"title":"End-to-End Training of Deep Visuomotor Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Pieter Abbeel, Sergey Levine, Trevor Darrell","submitted_at":"2015-04-02T22:23:51Z","abstract_excerpt":"Policy search methods can allow robots to learn control policies for a wide range of tasks, but practical applications of policy search often require hand-engineered components for perception, state estimation, and low-level control. In this paper, we aim to answer the following question: does training the perception and control systems jointly end-to-end provide better performance than training each component separately? To this end, we develop a method that can be used to learn policies that map raw image observations directly to torques at the robot's motors. The policies are represented by"},"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":"1504.00702","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-04-02T22:23:51Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"8fd5d89cb2cebd7c30fc86df8ad77930da36c917cd12854e296a2ba3e1f0c5e5","abstract_canon_sha256":"26c1775eff2953996686befdfad014aca5cc2241e1ba7a8d496e1ac66bd8be08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:54.753654Z","signature_b64":"+AEweKJRsKEP9kLpMxkNeoOlaQehc1TkeWcSGaS/DzzX/rRFr91IJP8hugqI9bGZd8LR0fp0sR3s3vgSNWomCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fb19a64cf97575e61f5e16d7722456996d96ea4b3ef881386818fd31191c69a","last_reissued_at":"2026-05-18T01:16:54.752940Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:54.752940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Training of Deep Visuomotor Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Pieter Abbeel, Sergey Levine, Trevor Darrell","submitted_at":"2015-04-02T22:23:51Z","abstract_excerpt":"Policy search methods can allow robots to learn control policies for a wide range of tasks, but practical applications of policy search often require hand-engineered components for perception, state estimation, and low-level control. In this paper, we aim to answer the following question: does training the perception and control systems jointly end-to-end provide better performance than training each component separately? To this end, we develop a method that can be used to learn policies that map raw image observations directly to torques at the robot's motors. The policies are represented by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.00702","kind":"arxiv","version":5},"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":"1504.00702","created_at":"2026-05-18T01:16:54.753058+00:00"},{"alias_kind":"arxiv_version","alias_value":"1504.00702v5","created_at":"2026-05-18T01:16:54.753058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.00702","created_at":"2026-05-18T01:16:54.753058+00:00"},{"alias_kind":"pith_short_12","alias_value":"B6YZUZGPS5LV","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"B6YZUZGPS5LV4YPV","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"B6YZUZGP","created_at":"2026-05-18T12:29:14.074870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.14598","citing_title":"DSSP: Diffusion State Space Policy with Full-History Encoding","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19029","citing_title":"Distributionally Robust Control via Stein Variational Inference for Contact-Rich Manipulation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13428","citing_title":"SID: Sliding into Distribution for Robust Few-Demonstration Manipulation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"1509.02971","citing_title":"Continuous control with deep reinforcement learning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B6YZUZGPS5LV4YPV4FWXOISFNG","json":"https://pith.science/pith/B6YZUZGPS5LV4YPV4FWXOISFNG.json","graph_json":"https://pith.science/api/pith-number/B6YZUZGPS5LV4YPV4FWXOISFNG/graph.json","events_json":"https://pith.science/api/pith-number/B6YZUZGPS5LV4YPV4FWXOISFNG/events.json","paper":"https://pith.science/paper/B6YZUZGP"},"agent_actions":{"view_html":"https://pith.science/pith/B6YZUZGPS5LV4YPV4FWXOISFNG","download_json":"https://pith.science/pith/B6YZUZGPS5LV4YPV4FWXOISFNG.json","view_paper":"https://pith.science/paper/B6YZUZGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1504.00702&json=true","fetch_graph":"https://pith.science/api/pith-number/B6YZUZGPS5LV4YPV4FWXOISFNG/graph.json","fetch_events":"https://pith.science/api/pith-number/B6YZUZGPS5LV4YPV4FWXOISFNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B6YZUZGPS5LV4YPV4FWXOISFNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B6YZUZGPS5LV4YPV4FWXOISFNG/action/storage_attestation","attest_author":"https://pith.science/pith/B6YZUZGPS5LV4YPV4FWXOISFNG/action/author_attestation","sign_citation":"https://pith.science/pith/B6YZUZGPS5LV4YPV4FWXOISFNG/action/citation_signature","submit_replication":"https://pith.science/pith/B6YZUZGPS5LV4YPV4FWXOISFNG/action/replication_record"}},"created_at":"2026-05-18T01:16:54.753058+00:00","updated_at":"2026-05-18T01:16:54.753058+00:00"}