{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:A7JKMBJBOTSAKK4SDP6KSLQGGD","short_pith_number":"pith:A7JKMBJB","schema_version":"1.0","canonical_sha256":"07d2a6052174e4052b921bfca92e0630df48df843c05b1016cee90b93b916600","source":{"kind":"arxiv","id":"1707.05110","version":1},"attestation_state":"computed","paper":{"title":"Control of a Quadrotor with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Inkyu Sa, Jemin Hwangbo, Marco Hutter, Roland Siegwart","submitted_at":"2017-07-17T11:44:13Z","abstract_excerpt":"In this paper, we present a method to control a quadrotor with a neural network trained using reinforcement learning techniques. With reinforcement learning, a common network can be trained to directly map state to actuator command making any predefined control structure obsolete for training. Moreover, we present a new learning algorithm which differs from the existing ones in certain aspects. Our algorithm is conservative but stable for complicated tasks. We found that it is more applicable to controlling a quadrotor than existing algorithms. We demonstrate the performance of the trained pol"},"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":"1707.05110","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-07-17T11:44:13Z","cross_cats_sorted":[],"title_canon_sha256":"f73eb53d8a9ba79ebefe84addca5e41419fc79895f7fdaeb880c9983ea78c4ec","abstract_canon_sha256":"1b631a9141a9f6a2aec78c32ad7626d0992015e07ccbc5f16d37b202fe8e0be7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:11.360169Z","signature_b64":"5HHrGzKna23fcZHXCCJ+4eyvhmjOAI+zfuZn6nb7f+/4NOU2XxHkAndkIV4Xj0ooCkCxNAWYDIXJhgrV3/yVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07d2a6052174e4052b921bfca92e0630df48df843c05b1016cee90b93b916600","last_reissued_at":"2026-05-18T00:40:11.359739Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:11.359739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Control of a Quadrotor with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Inkyu Sa, Jemin Hwangbo, Marco Hutter, Roland Siegwart","submitted_at":"2017-07-17T11:44:13Z","abstract_excerpt":"In this paper, we present a method to control a quadrotor with a neural network trained using reinforcement learning techniques. With reinforcement learning, a common network can be trained to directly map state to actuator command making any predefined control structure obsolete for training. Moreover, we present a new learning algorithm which differs from the existing ones in certain aspects. Our algorithm is conservative but stable for complicated tasks. We found that it is more applicable to controlling a quadrotor than existing algorithms. We demonstrate the performance of the trained pol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.05110","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":"1707.05110","created_at":"2026-05-18T00:40:11.359799+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.05110v1","created_at":"2026-05-18T00:40:11.359799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.05110","created_at":"2026-05-18T00:40:11.359799+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7JKMBJBOTSA","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7JKMBJBOTSAKK4S","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7JKMBJB","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2501.18490","citing_title":"Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotor","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19202","citing_title":"Aerial Inspection Behaviors via RL-based Quadrotor Control for Under-canopy Forest Environments","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7JKMBJBOTSAKK4SDP6KSLQGGD","json":"https://pith.science/pith/A7JKMBJBOTSAKK4SDP6KSLQGGD.json","graph_json":"https://pith.science/api/pith-number/A7JKMBJBOTSAKK4SDP6KSLQGGD/graph.json","events_json":"https://pith.science/api/pith-number/A7JKMBJBOTSAKK4SDP6KSLQGGD/events.json","paper":"https://pith.science/paper/A7JKMBJB"},"agent_actions":{"view_html":"https://pith.science/pith/A7JKMBJBOTSAKK4SDP6KSLQGGD","download_json":"https://pith.science/pith/A7JKMBJBOTSAKK4SDP6KSLQGGD.json","view_paper":"https://pith.science/paper/A7JKMBJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.05110&json=true","fetch_graph":"https://pith.science/api/pith-number/A7JKMBJBOTSAKK4SDP6KSLQGGD/graph.json","fetch_events":"https://pith.science/api/pith-number/A7JKMBJBOTSAKK4SDP6KSLQGGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7JKMBJBOTSAKK4SDP6KSLQGGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7JKMBJBOTSAKK4SDP6KSLQGGD/action/storage_attestation","attest_author":"https://pith.science/pith/A7JKMBJBOTSAKK4SDP6KSLQGGD/action/author_attestation","sign_citation":"https://pith.science/pith/A7JKMBJBOTSAKK4SDP6KSLQGGD/action/citation_signature","submit_replication":"https://pith.science/pith/A7JKMBJBOTSAKK4SDP6KSLQGGD/action/replication_record"}},"created_at":"2026-05-18T00:40:11.359799+00:00","updated_at":"2026-05-18T00:40:11.359799+00:00"}