{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KS6RW67SRSSPBBLLY2L4SDNZHQ","short_pith_number":"pith:KS6RW67S","schema_version":"1.0","canonical_sha256":"54bd1b7bf28ca4f0856bc697c90db93c08846dc68b5383faa62c44dd4096fbf2","source":{"kind":"arxiv","id":"1710.00336","version":2},"attestation_state":"computed","paper":{"title":"Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hangjun Ye, Xiangxiang Chu","submitted_at":"2017-10-01T11:43:10Z","abstract_excerpt":"Deep reinforcement learning for multi-agent cooperation and competition has been a hot topic recently. This paper focuses on cooperative multi-agent problem based on actor-critic methods under local observations settings. Multi agent deep deterministic policy gradient obtained state of art results for some multi-agent games, whereas, it cannot scale well with growing amount of agents. In order to boost scalability, we propose a parameter sharing deterministic policy gradient method with three variants based on neural networks, including actor-critic sharing, actor sharing and actor sharing wit"},"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":"1710.00336","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-10-01T11:43:10Z","cross_cats_sorted":[],"title_canon_sha256":"32060b062a0254a50e82baadd6e23f3aeea9a84db952249043537b31491d1290","abstract_canon_sha256":"9304300f71164b1e0109a65cb187cea8c18273fea3e7bca243844a43bc15f09e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:47.822684Z","signature_b64":"dvalGWXsQufENTzi4YY4DO7qgLoNoWzy3uaX8yOoEyINv72zeOdaRl/QTpPWgqd3IvJdObhkz2pVMkgCusYvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54bd1b7bf28ca4f0856bc697c90db93c08846dc68b5383faa62c44dd4096fbf2","last_reissued_at":"2026-05-18T00:33:47.822110Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:47.822110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter Sharing Deep Deterministic Policy Gradient for Cooperative Multi-agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hangjun Ye, Xiangxiang Chu","submitted_at":"2017-10-01T11:43:10Z","abstract_excerpt":"Deep reinforcement learning for multi-agent cooperation and competition has been a hot topic recently. This paper focuses on cooperative multi-agent problem based on actor-critic methods under local observations settings. Multi agent deep deterministic policy gradient obtained state of art results for some multi-agent games, whereas, it cannot scale well with growing amount of agents. In order to boost scalability, we propose a parameter sharing deterministic policy gradient method with three variants based on neural networks, including actor-critic sharing, actor sharing and actor sharing wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00336","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":"1710.00336","created_at":"2026-05-18T00:33:47.822205+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.00336v2","created_at":"2026-05-18T00:33:47.822205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00336","created_at":"2026-05-18T00:33:47.822205+00:00"},{"alias_kind":"pith_short_12","alias_value":"KS6RW67SRSSP","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"KS6RW67SRSSPBBLL","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"KS6RW67S","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.14297","citing_title":"Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ","json":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ.json","graph_json":"https://pith.science/api/pith-number/KS6RW67SRSSPBBLLY2L4SDNZHQ/graph.json","events_json":"https://pith.science/api/pith-number/KS6RW67SRSSPBBLLY2L4SDNZHQ/events.json","paper":"https://pith.science/paper/KS6RW67S"},"agent_actions":{"view_html":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ","download_json":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ.json","view_paper":"https://pith.science/paper/KS6RW67S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.00336&json=true","fetch_graph":"https://pith.science/api/pith-number/KS6RW67SRSSPBBLLY2L4SDNZHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KS6RW67SRSSPBBLLY2L4SDNZHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ/action/storage_attestation","attest_author":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ/action/author_attestation","sign_citation":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ/action/citation_signature","submit_replication":"https://pith.science/pith/KS6RW67SRSSPBBLLY2L4SDNZHQ/action/replication_record"}},"created_at":"2026-05-18T00:33:47.822205+00:00","updated_at":"2026-05-18T00:33:47.822205+00:00"}