{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UV6Z5BXN3H4DIWA34TYTMJHK4J","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dfb9f068812522cadea5fc9450d2e2c2ca2440739b8f3ddab58a45677ed4e726","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-03T13:19:23Z","title_canon_sha256":"859fa64515c32d35a31f4c0f7d635401bc547c6ff21bab4a2fbc5fb2c78fbc4e"},"schema_version":"1.0","source":{"id":"2506.02849","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02849","created_at":"2026-06-23T02:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02849v3","created_at":"2026-06-23T02:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02849","created_at":"2026-06-23T02:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"UV6Z5BXN3H4D","created_at":"2026-06-23T02:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"UV6Z5BXN3H4DIWA3","created_at":"2026-06-23T02:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"UV6Z5BXN","created_at":"2026-06-23T02:12:32Z"}],"graph_snapshots":[{"event_id":"sha256:de082fc316323b13ff55b10ced592522583439e4abaa40e578d39087d3189960","target":"graph","created_at":"2026-06-23T02:12:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.02849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alejandro Sanchez Roncero, Olov Andersson, Petter Ogren, Yixi Cai","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-03T13:19:23Z","title":"Learned Controllers for Agile Quadrotors in Pursuit-Evasion Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02849","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d17351e1f185404dfb5fa933305fb907acc4c0dbe9d922b11237b03228cc50a9","target":"record","created_at":"2026-06-23T02:12:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dfb9f068812522cadea5fc9450d2e2c2ca2440739b8f3ddab58a45677ed4e726","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-03T13:19:23Z","title_canon_sha256":"859fa64515c32d35a31f4c0f7d635401bc547c6ff21bab4a2fbc5fb2c78fbc4e"},"schema_version":"1.0","source":{"id":"2506.02849","kind":"arxiv","version":3}},"canonical_sha256":"a57d9e86edd9f834581be4f13624eae27b5b0f11f8badd611a2592a8c4b27382","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a57d9e86edd9f834581be4f13624eae27b5b0f11f8badd611a2592a8c4b27382","first_computed_at":"2026-06-23T02:12:32.009872Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:12:32.009872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7So93yLFTvVK/hEIxl7AwJN3R1EVF4ZStpdxf1eCqtCj9JTWeLnlCmvPcmxje+sDZXepDDIOBQCkau2ICTz5BA==","signature_status":"signed_v1","signed_at":"2026-06-23T02:12:32.010384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02849","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d17351e1f185404dfb5fa933305fb907acc4c0dbe9d922b11237b03228cc50a9","sha256:de082fc316323b13ff55b10ced592522583439e4abaa40e578d39087d3189960"],"state_sha256":"d86144c0d75145d8cedb91f8233aefe3b71dec69018caf6d64d964f39e4b761e"}