{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:K6ZCWOPBT2NRY7XBX5NIV34GNR","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":"cb6f7418e5c80f419d247a54f20a73a59a552a5a188608875106dd26481001cb","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-17T20:07:30Z","title_canon_sha256":"cf43628c75adbbb4ef8e82b6738302e5d173bc6d7b0f7eb9719d90297d6a6547"},"schema_version":"1.0","source":{"id":"2305.10548","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10548","created_at":"2026-07-05T06:11:23Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10548v1","created_at":"2026-07-05T06:11:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10548","created_at":"2026-07-05T06:11:23Z"},{"alias_kind":"pith_short_12","alias_value":"K6ZCWOPBT2NR","created_at":"2026-07-05T06:11:23Z"},{"alias_kind":"pith_short_16","alias_value":"K6ZCWOPBT2NRY7XB","created_at":"2026-07-05T06:11:23Z"},{"alias_kind":"pith_short_8","alias_value":"K6ZCWOPB","created_at":"2026-07-05T06:11:23Z"}],"graph_snapshots":[{"event_id":"sha256:98ae13d15f934fefc206f393684afd30681b4692050d5e712b43bd0d709c591e","target":"graph","created_at":"2026-07-05T06:11:23Z","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/2305.10548/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The discovery of individual objectives in collective behavior of complex dynamical systems such as fish schools and bacteria colonies is a long-standing challenge. Inverse reinforcement learning is a potent approach for addressing this challenge but its applicability to dynamical systems, involving continuous state-action spaces and multiple interacting agents, has been limited. In this study, we tackle this challenge by introducing an off-policy inverse multi-agent reinforcement learning algorithm (IMARL). Our approach combines the ReF-ER techniques with guided cost learning. By leveraging de","authors_text":"Daniel Waelchli, Pascal Weber, Petros Koumoutsakos","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-17T20:07:30Z","title":"Discovering Individual Rewards in Collective Behavior through Inverse Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10548","kind":"arxiv","version":1},"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":"sha256:3234a2afe47b37474e55c62d9e3b0f3db93e0207fc0714c346e32f01983733de","target":"record","created_at":"2026-07-05T06:11:23Z","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":"cb6f7418e5c80f419d247a54f20a73a59a552a5a188608875106dd26481001cb","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-17T20:07:30Z","title_canon_sha256":"cf43628c75adbbb4ef8e82b6738302e5d173bc6d7b0f7eb9719d90297d6a6547"},"schema_version":"1.0","source":{"id":"2305.10548","kind":"arxiv","version":1}},"canonical_sha256":"57b22b39e19e9b1c7ee1bf5a8aef866c62efe90a049bde658b07502ce7f65804","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57b22b39e19e9b1c7ee1bf5a8aef866c62efe90a049bde658b07502ce7f65804","first_computed_at":"2026-07-05T06:11:23.549805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:23.549805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KjY7Eu/fOZK+YLQG07pKlJQSNpBReW2zs5EXKL2afqbA6d4wpwXQc2KIh7Cn5gnUlKR8LauyJjpjWnaQKWFtCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:23.550260Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10548","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3234a2afe47b37474e55c62d9e3b0f3db93e0207fc0714c346e32f01983733de","sha256:98ae13d15f934fefc206f393684afd30681b4692050d5e712b43bd0d709c591e"],"state_sha256":"e63cef9b3b14d78751dfd0bb0f1e3380f7814b973e6efebf651021189f1afc18"}