{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UV6Z5BXN3H4DIWA34TYTMJHK4J","short_pith_number":"pith:UV6Z5BXN","schema_version":"1.0","canonical_sha256":"a57d9e86edd9f834581be4f13624eae27b5b0f11f8badd611a2592a8c4b27382","source":{"kind":"arxiv","id":"2506.02849","version":3},"attestation_state":"computed","paper":{"title":"Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Alejandro Sanchez Roncero, Olov Andersson, Petter Ogren, Yixi Cai","submitted_at":"2025-06-03T13:19:23Z","abstract_excerpt":"In this letter we study 1v1 quadrotor pursuit-evasion, where a pursuer and an evader are trained via reinforcement learning (RL) by competing against each other. Such adversarial settings face well-known challenges: each agent's policy changes during training, creating a non-stationary environment; agents might overfit to the current opponent and forget earlier strategies (catastrophic forgetting); and the competitive dynamics can cause strategy cycling or policy collapse. To address these issues, we propose Asynchronous Multi-Stage Population-Based training with Hedge sampling (AMSPBH), a met"},"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":"2506.02849","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-03T13:19:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"859fa64515c32d35a31f4c0f7d635401bc547c6ff21bab4a2fbc5fb2c78fbc4e","abstract_canon_sha256":"dfb9f068812522cadea5fc9450d2e2c2ca2440739b8f3ddab58a45677ed4e726"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:12:32.010384Z","signature_b64":"7So93yLFTvVK/hEIxl7AwJN3R1EVF4ZStpdxf1eCqtCj9JTWeLnlCmvPcmxje+sDZXepDDIOBQCkau2ICTz5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a57d9e86edd9f834581be4f13624eae27b5b0f11f8badd611a2592a8c4b27382","last_reissued_at":"2026-06-23T02:12:32.009872Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:12:32.009872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Alejandro Sanchez Roncero, Olov Andersson, Petter Ogren, Yixi Cai","submitted_at":"2025-06-03T13:19:23Z","abstract_excerpt":"In this letter we study 1v1 quadrotor pursuit-evasion, where a pursuer and an evader are trained via reinforcement learning (RL) by competing against each other. Such adversarial settings face well-known challenges: each agent's policy changes during training, creating a non-stationary environment; agents might overfit to the current opponent and forget earlier strategies (catastrophic forgetting); and the competitive dynamics can cause strategy cycling or policy collapse. To address these issues, we propose Asynchronous Multi-Stage Population-Based training with Hedge sampling (AMSPBH), a met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02849","kind":"arxiv","version":3},"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/2506.02849/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":"2506.02849","created_at":"2026-06-23T02:12:32.009930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02849v3","created_at":"2026-06-23T02:12:32.009930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02849","created_at":"2026-06-23T02:12:32.009930+00:00"},{"alias_kind":"pith_short_12","alias_value":"UV6Z5BXN3H4D","created_at":"2026-06-23T02:12:32.009930+00:00"},{"alias_kind":"pith_short_16","alias_value":"UV6Z5BXN3H4DIWA3","created_at":"2026-06-23T02:12:32.009930+00:00"},{"alias_kind":"pith_short_8","alias_value":"UV6Z5BXN","created_at":"2026-06-23T02:12:32.009930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.02472","citing_title":"Learning Agile Intruder Interception using Differentiable Quadrotor Dynamics","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UV6Z5BXN3H4DIWA34TYTMJHK4J","json":"https://pith.science/pith/UV6Z5BXN3H4DIWA34TYTMJHK4J.json","graph_json":"https://pith.science/api/pith-number/UV6Z5BXN3H4DIWA34TYTMJHK4J/graph.json","events_json":"https://pith.science/api/pith-number/UV6Z5BXN3H4DIWA34TYTMJHK4J/events.json","paper":"https://pith.science/paper/UV6Z5BXN"},"agent_actions":{"view_html":"https://pith.science/pith/UV6Z5BXN3H4DIWA34TYTMJHK4J","download_json":"https://pith.science/pith/UV6Z5BXN3H4DIWA34TYTMJHK4J.json","view_paper":"https://pith.science/paper/UV6Z5BXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02849&json=true","fetch_graph":"https://pith.science/api/pith-number/UV6Z5BXN3H4DIWA34TYTMJHK4J/graph.json","fetch_events":"https://pith.science/api/pith-number/UV6Z5BXN3H4DIWA34TYTMJHK4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UV6Z5BXN3H4DIWA34TYTMJHK4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UV6Z5BXN3H4DIWA34TYTMJHK4J/action/storage_attestation","attest_author":"https://pith.science/pith/UV6Z5BXN3H4DIWA34TYTMJHK4J/action/author_attestation","sign_citation":"https://pith.science/pith/UV6Z5BXN3H4DIWA34TYTMJHK4J/action/citation_signature","submit_replication":"https://pith.science/pith/UV6Z5BXN3H4DIWA34TYTMJHK4J/action/replication_record"}},"created_at":"2026-06-23T02:12:32.009930+00:00","updated_at":"2026-06-23T02:12:32.009930+00:00"}