{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:LGEZWJKDD3H2JUHCVCBGQDJYYU","short_pith_number":"pith:LGEZWJKD","schema_version":"1.0","canonical_sha256":"59899b25431ecfa4d0e2a882680d38c5115a30316106e90b23e8115952cba107","source":{"kind":"arxiv","id":"1602.05450","version":2},"attestation_state":"computed","paper":{"title":"Inverse Reinforcement Learning in Swarm Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.SY"],"primary_cat":"stat.ML","authors_text":"Abdelhak M. Zoubir, Adrian \\v{S}o\\v{s}i\\'c, Heinz Koeppl, Wasiur R. KhudaBukhsh","submitted_at":"2016-02-17T15:19:56Z","abstract_excerpt":"Inverse reinforcement learning (IRL) has become a useful tool for learning behavioral models from demonstration data. However, IRL remains mostly unexplored for multi-agent systems. In this paper, we show how the principle of IRL can be extended to homogeneous large-scale problems, inspired by the collective swarming behavior of natural systems. In particular, we make the following contributions to the field: 1) We introduce the swarMDP framework, a sub-class of decentralized partially observable Markov decision processes endowed with a swarm characterization. 2) Exploiting the inherent homoge"},"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":"1602.05450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-17T15:19:56Z","cross_cats_sorted":["cs.AI","cs.MA","cs.SY"],"title_canon_sha256":"f6b58f60f80203b00093bdb878dba45a1c1a037fd0cf56a762c3be9a13964582","abstract_canon_sha256":"9a0b7787634c8c7ff7177d5a8c29e0bf659eafdf82ae542095b1dcfa775dbb85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:01.332652Z","signature_b64":"3obe0xIGmQRaUSkY5IU8Sw7U0CygmAaMRgmYnI6UQhV+eszTGCGLwS5xIULqPemnZ2nUaHVd2rwcAB8QxR49Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59899b25431ecfa4d0e2a882680d38c5115a30316106e90b23e8115952cba107","last_reissued_at":"2026-05-18T00:48:01.332033Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:01.332033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inverse Reinforcement Learning in Swarm Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.SY"],"primary_cat":"stat.ML","authors_text":"Abdelhak M. Zoubir, Adrian \\v{S}o\\v{s}i\\'c, Heinz Koeppl, Wasiur R. KhudaBukhsh","submitted_at":"2016-02-17T15:19:56Z","abstract_excerpt":"Inverse reinforcement learning (IRL) has become a useful tool for learning behavioral models from demonstration data. However, IRL remains mostly unexplored for multi-agent systems. In this paper, we show how the principle of IRL can be extended to homogeneous large-scale problems, inspired by the collective swarming behavior of natural systems. In particular, we make the following contributions to the field: 1) We introduce the swarMDP framework, a sub-class of decentralized partially observable Markov decision processes endowed with a swarm characterization. 2) Exploiting the inherent homoge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.05450","kind":"arxiv","version":2},"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":"1602.05450","created_at":"2026-05-18T00:48:01.332129+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.05450v2","created_at":"2026-05-18T00:48:01.332129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.05450","created_at":"2026-05-18T00:48:01.332129+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGEZWJKDD3H2","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGEZWJKDD3H2JUHC","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGEZWJKD","created_at":"2026-05-18T12:30:29.479603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU","json":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU.json","graph_json":"https://pith.science/api/pith-number/LGEZWJKDD3H2JUHCVCBGQDJYYU/graph.json","events_json":"https://pith.science/api/pith-number/LGEZWJKDD3H2JUHCVCBGQDJYYU/events.json","paper":"https://pith.science/paper/LGEZWJKD"},"agent_actions":{"view_html":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU","download_json":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU.json","view_paper":"https://pith.science/paper/LGEZWJKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.05450&json=true","fetch_graph":"https://pith.science/api/pith-number/LGEZWJKDD3H2JUHCVCBGQDJYYU/graph.json","fetch_events":"https://pith.science/api/pith-number/LGEZWJKDD3H2JUHCVCBGQDJYYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU/action/storage_attestation","attest_author":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU/action/author_attestation","sign_citation":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU/action/citation_signature","submit_replication":"https://pith.science/pith/LGEZWJKDD3H2JUHCVCBGQDJYYU/action/replication_record"}},"created_at":"2026-05-18T00:48:01.332129+00:00","updated_at":"2026-05-18T00:48:01.332129+00:00"}