{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SN64RNZN6ONMCCSNNP4MPA7XV7","short_pith_number":"pith:SN64RNZN","schema_version":"1.0","canonical_sha256":"937dc8b72df39ac10a4d6bf8c783f7afe585c92ee75b415ed47ed15084645c16","source":{"kind":"arxiv","id":"2412.12442","version":1},"attestation_state":"computed","paper":{"title":"Multi-Task Reinforcement Learning for Quadrotors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Davide Scaramuzza, Elie Aljalbout, Ismail Geles, Jiaxu Xing, Yunlong Song","submitted_at":"2024-12-17T01:10:18Z","abstract_excerpt":"Reinforcement learning (RL) has shown great effectiveness in quadrotor control, enabling specialized policies to develop even human-champion-level performance in single-task scenarios. However, these specialized policies often struggle with novel tasks, requiring a complete retraining of the policy from scratch. To address this limitation, this paper presents a novel multi-task reinforcement learning (MTRL) framework tailored for quadrotor control, leveraging the shared physical dynamics of the platform to enhance sample efficiency and task performance. By employing a multi-critic architecture"},"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":"2412.12442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-17T01:10:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"961a3a4b9a19dd59af088e11bb2f3677d6536e357371437dd92f4e0ff24d6898","abstract_canon_sha256":"02aac9ec542c3c46b948f234bc727f8c01e9735d8749015605079293bcb09e10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:14.989835Z","signature_b64":"Kz5Ke0eFGAW6P9hRhdwGoGFywYrqshSe7RzVNApgXcUg9vQpqfi0ChQITfuXs2TtYLeaQuTYyWu4MjCADyceBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"937dc8b72df39ac10a4d6bf8c783f7afe585c92ee75b415ed47ed15084645c16","last_reissued_at":"2026-07-05T09:50:14.989402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:14.989402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Reinforcement Learning for Quadrotors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Davide Scaramuzza, Elie Aljalbout, Ismail Geles, Jiaxu Xing, Yunlong Song","submitted_at":"2024-12-17T01:10:18Z","abstract_excerpt":"Reinforcement learning (RL) has shown great effectiveness in quadrotor control, enabling specialized policies to develop even human-champion-level performance in single-task scenarios. However, these specialized policies often struggle with novel tasks, requiring a complete retraining of the policy from scratch. To address this limitation, this paper presents a novel multi-task reinforcement learning (MTRL) framework tailored for quadrotor control, leveraging the shared physical dynamics of the platform to enhance sample efficiency and task performance. By employing a multi-critic architecture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12442","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.12442/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2412.12442","created_at":"2026-07-05T09:50:14.989459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12442v1","created_at":"2026-07-05T09:50:14.989459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12442","created_at":"2026-07-05T09:50:14.989459+00:00"},{"alias_kind":"pith_short_12","alias_value":"SN64RNZN6ONM","created_at":"2026-07-05T09:50:14.989459+00:00"},{"alias_kind":"pith_short_16","alias_value":"SN64RNZN6ONMCCSN","created_at":"2026-07-05T09:50:14.989459+00:00"},{"alias_kind":"pith_short_8","alias_value":"SN64RNZN","created_at":"2026-07-05T09:50:14.989459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.00432","citing_title":"A Neural Network Mode for PX4 on Embedded Flight Controllers","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SN64RNZN6ONMCCSNNP4MPA7XV7","json":"https://pith.science/pith/SN64RNZN6ONMCCSNNP4MPA7XV7.json","graph_json":"https://pith.science/api/pith-number/SN64RNZN6ONMCCSNNP4MPA7XV7/graph.json","events_json":"https://pith.science/api/pith-number/SN64RNZN6ONMCCSNNP4MPA7XV7/events.json","paper":"https://pith.science/paper/SN64RNZN"},"agent_actions":{"view_html":"https://pith.science/pith/SN64RNZN6ONMCCSNNP4MPA7XV7","download_json":"https://pith.science/pith/SN64RNZN6ONMCCSNNP4MPA7XV7.json","view_paper":"https://pith.science/paper/SN64RNZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12442&json=true","fetch_graph":"https://pith.science/api/pith-number/SN64RNZN6ONMCCSNNP4MPA7XV7/graph.json","fetch_events":"https://pith.science/api/pith-number/SN64RNZN6ONMCCSNNP4MPA7XV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SN64RNZN6ONMCCSNNP4MPA7XV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SN64RNZN6ONMCCSNNP4MPA7XV7/action/storage_attestation","attest_author":"https://pith.science/pith/SN64RNZN6ONMCCSNNP4MPA7XV7/action/author_attestation","sign_citation":"https://pith.science/pith/SN64RNZN6ONMCCSNNP4MPA7XV7/action/citation_signature","submit_replication":"https://pith.science/pith/SN64RNZN6ONMCCSNNP4MPA7XV7/action/replication_record"}},"created_at":"2026-07-05T09:50:14.989459+00:00","updated_at":"2026-07-05T09:50:14.989459+00:00"}