{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:PW4GLZGWMQRTZXDAU7UQQOR45Z","short_pith_number":"pith:PW4GLZGW","schema_version":"1.0","canonical_sha256":"7db865e4d664233cdc60a7e9083a3cee4871ab5fbcabbd1dbbf3701e760bf460","source":{"kind":"arxiv","id":"1511.03791","version":2},"attestation_state":"computed","paper":{"title":"Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ben Upcroft, Fangyi Zhang, J\\\"urgen Leitner, Michael Milford, Peter Corke","submitted_at":"2015-11-12T06:19:59Z","abstract_excerpt":"This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixel images and without any prior knowledge of configuration is shown for the first time. We build upon the success of recent deep reinforcement learning and develop a system for learning target reaching with a three-joint robot manipulator using external visual observation. A Deep Q Network (DQN) was demonstrated to perform target reaching after training in simulation. Transferring the network to real h"},"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":"1511.03791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-12T06:19:59Z","cross_cats_sorted":["cs.CV","cs.RO"],"title_canon_sha256":"df5bd41ade444484b975736142b39ba2510d7987bc330feefda50eb58ef4c4dc","abstract_canon_sha256":"dfeec32eccbc122bc9e7d754c02d69049e19778ecddcdd5cc85316ce5b1882f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:59.755437Z","signature_b64":"t1bobJW8pHHe+3ZXI5GwNgGs0vFPxk83aKc+KbnrOOlUY3X/TxlzyWKQtrA65FtqLV5vtncmwz58knXZF4WPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7db865e4d664233cdc60a7e9083a3cee4871ab5fbcabbd1dbbf3701e760bf460","last_reissued_at":"2026-05-18T01:26:59.754714Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:59.754714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Ben Upcroft, Fangyi Zhang, J\\\"urgen Leitner, Michael Milford, Peter Corke","submitted_at":"2015-11-12T06:19:59Z","abstract_excerpt":"This paper introduces a machine learning based system for controlling a robotic manipulator with visual perception only. The capability to autonomously learn robot controllers solely from raw-pixel images and without any prior knowledge of configuration is shown for the first time. We build upon the success of recent deep reinforcement learning and develop a system for learning target reaching with a three-joint robot manipulator using external visual observation. A Deep Q Network (DQN) was demonstrated to perform target reaching after training in simulation. Transferring the network to real h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.03791","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":"1511.03791","created_at":"2026-05-18T01:26:59.754822+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.03791v2","created_at":"2026-05-18T01:26:59.754822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.03791","created_at":"2026-05-18T01:26:59.754822+00:00"},{"alias_kind":"pith_short_12","alias_value":"PW4GLZGWMQRT","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_16","alias_value":"PW4GLZGWMQRTZXDA","created_at":"2026-05-18T12:29:37.295048+00:00"},{"alias_kind":"pith_short_8","alias_value":"PW4GLZGW","created_at":"2026-05-18T12:29:37.295048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2511.14427","citing_title":"Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PW4GLZGWMQRTZXDAU7UQQOR45Z","json":"https://pith.science/pith/PW4GLZGWMQRTZXDAU7UQQOR45Z.json","graph_json":"https://pith.science/api/pith-number/PW4GLZGWMQRTZXDAU7UQQOR45Z/graph.json","events_json":"https://pith.science/api/pith-number/PW4GLZGWMQRTZXDAU7UQQOR45Z/events.json","paper":"https://pith.science/paper/PW4GLZGW"},"agent_actions":{"view_html":"https://pith.science/pith/PW4GLZGWMQRTZXDAU7UQQOR45Z","download_json":"https://pith.science/pith/PW4GLZGWMQRTZXDAU7UQQOR45Z.json","view_paper":"https://pith.science/paper/PW4GLZGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.03791&json=true","fetch_graph":"https://pith.science/api/pith-number/PW4GLZGWMQRTZXDAU7UQQOR45Z/graph.json","fetch_events":"https://pith.science/api/pith-number/PW4GLZGWMQRTZXDAU7UQQOR45Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PW4GLZGWMQRTZXDAU7UQQOR45Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PW4GLZGWMQRTZXDAU7UQQOR45Z/action/storage_attestation","attest_author":"https://pith.science/pith/PW4GLZGWMQRTZXDAU7UQQOR45Z/action/author_attestation","sign_citation":"https://pith.science/pith/PW4GLZGWMQRTZXDAU7UQQOR45Z/action/citation_signature","submit_replication":"https://pith.science/pith/PW4GLZGWMQRTZXDAU7UQQOR45Z/action/replication_record"}},"created_at":"2026-05-18T01:26:59.754822+00:00","updated_at":"2026-05-18T01:26:59.754822+00:00"}