{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XU7GCZD4LVOCYISK7SQ6JNJZ2O","short_pith_number":"pith:XU7GCZD4","schema_version":"1.0","canonical_sha256":"bd3e61647c5d5c2c224afca1e4b539d3838553d9777002353590b7f805295b12","source":{"kind":"arxiv","id":"1807.06613","version":3},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning for Swarm Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","stat.ML"],"primary_cat":"cs.MA","authors_text":"Adrian \\v{S}o\\v{s}i\\'c, Gerhard Neumann, Maximilian H\\\"uttenrauch","submitted_at":"2018-07-17T18:27:03Z","abstract_excerpt":"Recently, deep reinforcement learning (RL) methods have been applied successfully to multi-agent scenarios. Typically, these methods rely on a concatenation of agent states to represent the information content required for decentralized decision making. However, concatenation scales poorly to swarm systems with a large number of homogeneous agents as it does not exploit the fundamental properties inherent to these systems: (i) the agents in the swarm are interchangeable and (ii) the exact number of agents in the swarm is irrelevant. Therefore, we propose a new state representation for deep mul"},"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":"1807.06613","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2018-07-17T18:27:03Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","stat.ML"],"title_canon_sha256":"99bb0046c4b8b13090f177509669bf57946139e69b837ff5ed7ed0ac53716cac","abstract_canon_sha256":"7e61d6d4770697831c2c556737ce60952ad7da4c475f576f6ff5740e9be33928"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:02.913373Z","signature_b64":"AqK8H4VDmkllsXnUvf+UYXmLCo4yZEoiThoJ+5/4akL6UzZkRnUyI85vgiuMoBPOZSf9AvkuYlrfvHdBlpaeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd3e61647c5d5c2c224afca1e4b539d3838553d9777002353590b7f805295b12","last_reissued_at":"2026-05-17T23:44:02.912863Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:02.912863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Swarm Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","stat.ML"],"primary_cat":"cs.MA","authors_text":"Adrian \\v{S}o\\v{s}i\\'c, Gerhard Neumann, Maximilian H\\\"uttenrauch","submitted_at":"2018-07-17T18:27:03Z","abstract_excerpt":"Recently, deep reinforcement learning (RL) methods have been applied successfully to multi-agent scenarios. Typically, these methods rely on a concatenation of agent states to represent the information content required for decentralized decision making. However, concatenation scales poorly to swarm systems with a large number of homogeneous agents as it does not exploit the fundamental properties inherent to these systems: (i) the agents in the swarm are interchangeable and (ii) the exact number of agents in the swarm is irrelevant. Therefore, we propose a new state representation for deep mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06613","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":""},"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":"1807.06613","created_at":"2026-05-17T23:44:02.912931+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.06613v3","created_at":"2026-05-17T23:44:02.912931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06613","created_at":"2026-05-17T23:44:02.912931+00:00"},{"alias_kind":"pith_short_12","alias_value":"XU7GCZD4LVOC","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XU7GCZD4LVOCYISK","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XU7GCZD4","created_at":"2026-05-18T12:33:01.666342+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/XU7GCZD4LVOCYISK7SQ6JNJZ2O","json":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O.json","graph_json":"https://pith.science/api/pith-number/XU7GCZD4LVOCYISK7SQ6JNJZ2O/graph.json","events_json":"https://pith.science/api/pith-number/XU7GCZD4LVOCYISK7SQ6JNJZ2O/events.json","paper":"https://pith.science/paper/XU7GCZD4"},"agent_actions":{"view_html":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O","download_json":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O.json","view_paper":"https://pith.science/paper/XU7GCZD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.06613&json=true","fetch_graph":"https://pith.science/api/pith-number/XU7GCZD4LVOCYISK7SQ6JNJZ2O/graph.json","fetch_events":"https://pith.science/api/pith-number/XU7GCZD4LVOCYISK7SQ6JNJZ2O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O/action/storage_attestation","attest_author":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O/action/author_attestation","sign_citation":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O/action/citation_signature","submit_replication":"https://pith.science/pith/XU7GCZD4LVOCYISK7SQ6JNJZ2O/action/replication_record"}},"created_at":"2026-05-17T23:44:02.912931+00:00","updated_at":"2026-05-17T23:44:02.912931+00:00"}