{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:R5RD77UBHDTQEKSSDNOBY2KZYR","short_pith_number":"pith:R5RD77UB","schema_version":"1.0","canonical_sha256":"8f623ffe8138e7022a521b5c1c6959c4491e6b48930aa60b3963ff725157b5cf","source":{"kind":"arxiv","id":"1805.08776","version":1},"attestation_state":"computed","paper":{"title":"Scalable Centralized Deep Multi-Agent Reinforcement Learning via Policy Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alejandro Ribeiro, Arbaaz Khan, Clark Zhang, Daniel D. Lee, Vijay Kumar","submitted_at":"2018-05-22T00:31:03Z","abstract_excerpt":"In this paper, we explore using deep reinforcement learning for problems with multiple agents. Most existing methods for deep multi-agent reinforcement learning consider only a small number of agents. When the number of agents increases, the dimensionality of the input and control spaces increase as well, and these methods do not scale well. To address this, we propose casting the multi-agent reinforcement learning problem as a distributed optimization problem. Our algorithm assumes that for multi-agent settings, policies of individual agents in a given population live close to each other in p"},"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":"1805.08776","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T00:31:03Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"c961e3c436b05e70ce48f2d963d440039acc94173aa53ecb97ee6294bcb7db67","abstract_canon_sha256":"1f6ab4cf8e42b9e22a8203f5e7fabbee061e12aa2e3668464f63d3a2505e9e51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:09.415086Z","signature_b64":"beumfw/YmOYAv8tAPR9wPNbs5ge6TMfiatURFEL2mhIDmFw0PHTln72yoY3tCDx3DPDe1K5yrH3U9bLRduOGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f623ffe8138e7022a521b5c1c6959c4491e6b48930aa60b3963ff725157b5cf","last_reissued_at":"2026-05-18T00:15:09.414669Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:09.414669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Centralized Deep Multi-Agent Reinforcement Learning via Policy Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alejandro Ribeiro, Arbaaz Khan, Clark Zhang, Daniel D. Lee, Vijay Kumar","submitted_at":"2018-05-22T00:31:03Z","abstract_excerpt":"In this paper, we explore using deep reinforcement learning for problems with multiple agents. Most existing methods for deep multi-agent reinforcement learning consider only a small number of agents. When the number of agents increases, the dimensionality of the input and control spaces increase as well, and these methods do not scale well. To address this, we propose casting the multi-agent reinforcement learning problem as a distributed optimization problem. Our algorithm assumes that for multi-agent settings, policies of individual agents in a given population live close to each other in p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08776","kind":"arxiv","version":1},"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":"1805.08776","created_at":"2026-05-18T00:15:09.414740+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08776v1","created_at":"2026-05-18T00:15:09.414740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08776","created_at":"2026-05-18T00:15:09.414740+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5RD77UBHDTQ","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5RD77UBHDTQEKSS","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5RD77UB","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.05300","citing_title":"Learning Safe Unlabeled Multi-Robot Planning with Motion Constraints","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R5RD77UBHDTQEKSSDNOBY2KZYR","json":"https://pith.science/pith/R5RD77UBHDTQEKSSDNOBY2KZYR.json","graph_json":"https://pith.science/api/pith-number/R5RD77UBHDTQEKSSDNOBY2KZYR/graph.json","events_json":"https://pith.science/api/pith-number/R5RD77UBHDTQEKSSDNOBY2KZYR/events.json","paper":"https://pith.science/paper/R5RD77UB"},"agent_actions":{"view_html":"https://pith.science/pith/R5RD77UBHDTQEKSSDNOBY2KZYR","download_json":"https://pith.science/pith/R5RD77UBHDTQEKSSDNOBY2KZYR.json","view_paper":"https://pith.science/paper/R5RD77UB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08776&json=true","fetch_graph":"https://pith.science/api/pith-number/R5RD77UBHDTQEKSSDNOBY2KZYR/graph.json","fetch_events":"https://pith.science/api/pith-number/R5RD77UBHDTQEKSSDNOBY2KZYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5RD77UBHDTQEKSSDNOBY2KZYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5RD77UBHDTQEKSSDNOBY2KZYR/action/storage_attestation","attest_author":"https://pith.science/pith/R5RD77UBHDTQEKSSDNOBY2KZYR/action/author_attestation","sign_citation":"https://pith.science/pith/R5RD77UBHDTQEKSSDNOBY2KZYR/action/citation_signature","submit_replication":"https://pith.science/pith/R5RD77UBHDTQEKSSDNOBY2KZYR/action/replication_record"}},"created_at":"2026-05-18T00:15:09.414740+00:00","updated_at":"2026-05-18T00:15:09.414740+00:00"}