{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TEWEMRT6PKXPIRDP5GMATQOVRL","short_pith_number":"pith:TEWEMRT6","schema_version":"1.0","canonical_sha256":"992c46467e7aaef4446fe99809c1d58afd6650e23021b364e153f6a90995c6c4","source":{"kind":"arxiv","id":"1902.02311","version":4},"attestation_state":"computed","paper":{"title":"Decentralized Multi-Agents by Imitation of a Centralized Controller","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.MA","authors_text":"Alex Tong Lin, Gary Hewer, Guido Montufar, Katia Estabridis, Mark J. Debord, Stanley Osher","submitted_at":"2019-02-06T18:14:31Z","abstract_excerpt":"We consider a multi-agent reinforcement learning problem where each agent seeks to maximize a shared reward while interacting with other agents, and they may or may not be able to communicate. Typically the agents do not have access to other agent policies and thus each agent is situated in a non-stationary and partially-observable environment. In order to obtain multi-agents that act in a decentralized manner, we introduce a novel algorithm under the popular framework of centralized training, but decentralized execution. This training framework first obtains solutions to a multi-agent problem"},"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":"1902.02311","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-02-06T18:14:31Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"93dc4d61fd6011b205dab185bbd1b9609d7d38ab8f586659c0ac546ed1aedc08","abstract_canon_sha256":"77985b547cd390d5cc7824260a7adcbb83a0ea394ef76009f83d4afce64f30fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T20:13:52.308369Z","signature_b64":"N4EylY644lRiaJOFBN1TdiwrvRoEViUUnHQmul2Jyn7tAsOAMgMiMhtbDErTY6/foJkILLyMa0RXXa7cBl4vAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"992c46467e7aaef4446fe99809c1d58afd6650e23021b364e153f6a90995c6c4","last_reissued_at":"2026-06-04T20:13:52.307930Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T20:13:52.307930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Multi-Agents by Imitation of a Centralized Controller","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.MA","authors_text":"Alex Tong Lin, Gary Hewer, Guido Montufar, Katia Estabridis, Mark J. Debord, Stanley Osher","submitted_at":"2019-02-06T18:14:31Z","abstract_excerpt":"We consider a multi-agent reinforcement learning problem where each agent seeks to maximize a shared reward while interacting with other agents, and they may or may not be able to communicate. Typically the agents do not have access to other agent policies and thus each agent is situated in a non-stationary and partially-observable environment. In order to obtain multi-agents that act in a decentralized manner, we introduce a novel algorithm under the popular framework of centralized training, but decentralized execution. This training framework first obtains solutions to a multi-agent problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02311","kind":"arxiv","version":4},"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/1902.02311/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":"1902.02311","created_at":"2026-06-04T20:13:52.307993+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.02311v4","created_at":"2026-06-04T20:13:52.307993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02311","created_at":"2026-06-04T20:13:52.307993+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEWEMRT6PKXP","created_at":"2026-06-04T20:13:52.307993+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEWEMRT6PKXPIRDP","created_at":"2026-06-04T20:13:52.307993+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEWEMRT6","created_at":"2026-06-04T20:13:52.307993+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/TEWEMRT6PKXPIRDP5GMATQOVRL","json":"https://pith.science/pith/TEWEMRT6PKXPIRDP5GMATQOVRL.json","graph_json":"https://pith.science/api/pith-number/TEWEMRT6PKXPIRDP5GMATQOVRL/graph.json","events_json":"https://pith.science/api/pith-number/TEWEMRT6PKXPIRDP5GMATQOVRL/events.json","paper":"https://pith.science/paper/TEWEMRT6"},"agent_actions":{"view_html":"https://pith.science/pith/TEWEMRT6PKXPIRDP5GMATQOVRL","download_json":"https://pith.science/pith/TEWEMRT6PKXPIRDP5GMATQOVRL.json","view_paper":"https://pith.science/paper/TEWEMRT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.02311&json=true","fetch_graph":"https://pith.science/api/pith-number/TEWEMRT6PKXPIRDP5GMATQOVRL/graph.json","fetch_events":"https://pith.science/api/pith-number/TEWEMRT6PKXPIRDP5GMATQOVRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEWEMRT6PKXPIRDP5GMATQOVRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEWEMRT6PKXPIRDP5GMATQOVRL/action/storage_attestation","attest_author":"https://pith.science/pith/TEWEMRT6PKXPIRDP5GMATQOVRL/action/author_attestation","sign_citation":"https://pith.science/pith/TEWEMRT6PKXPIRDP5GMATQOVRL/action/citation_signature","submit_replication":"https://pith.science/pith/TEWEMRT6PKXPIRDP5GMATQOVRL/action/replication_record"}},"created_at":"2026-06-04T20:13:52.307993+00:00","updated_at":"2026-06-04T20:13:52.307993+00:00"}