{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:H4FGSMKYRM5M3YBPYIQXBLHO3Q","short_pith_number":"pith:H4FGSMKY","schema_version":"1.0","canonical_sha256":"3f0a6931588b3acde02fc22170aceedc22e48a9959855eea2b53375bc9fb165c","source":{"kind":"arxiv","id":"1811.07029","version":1},"attestation_state":"computed","paper":{"title":"Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hangyu Mao, Zhengchao Zhang, Zhen Xiao, Zhibo Gong","submitted_at":"2018-11-13T11:30:29Z","abstract_excerpt":"Modelling and exploiting teammates' policies in cooperative multi-agent systems have long been an interest and also a big challenge for the reinforcement learning (RL) community. The interest lies in the fact that if the agent knows the teammates' policies, it can adjust its own policy accordingly to arrive at proper cooperations; while the challenge is that the agents' policies are changing continuously due to they are learning concurrently, which imposes difficulty to model the dynamic policies of teammates accurately. In this paper, we present \\emph{ATTention Multi-Agent Deep Deterministic "},"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":"1811.07029","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-13T11:30:29Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"0f1d9d78d9d900e1ba255deace00f62e084a583555aa5cff7b646ffa4632e794","abstract_canon_sha256":"4a8326afcaec7f9dfef2523a04338cd5e3f8820a14b036df8065f9421a2f0388"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:29.244875Z","signature_b64":"fJZcSrEb4pJUOhrUvHdL0LiJdLSvxAC/D+4k7q+zljEL6OGDctjf5uhdQ2v2Cjp0JtRfENZRhpqEShoTIcQ5Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f0a6931588b3acde02fc22170aceedc22e48a9959855eea2b53375bc9fb165c","last_reissued_at":"2026-05-18T00:00:29.244174Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:29.244174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hangyu Mao, Zhengchao Zhang, Zhen Xiao, Zhibo Gong","submitted_at":"2018-11-13T11:30:29Z","abstract_excerpt":"Modelling and exploiting teammates' policies in cooperative multi-agent systems have long been an interest and also a big challenge for the reinforcement learning (RL) community. The interest lies in the fact that if the agent knows the teammates' policies, it can adjust its own policy accordingly to arrive at proper cooperations; while the challenge is that the agents' policies are changing continuously due to they are learning concurrently, which imposes difficulty to model the dynamic policies of teammates accurately. In this paper, we present \\emph{ATTention Multi-Agent Deep Deterministic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.07029","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":"1811.07029","created_at":"2026-05-18T00:00:29.244274+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.07029v1","created_at":"2026-05-18T00:00:29.244274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.07029","created_at":"2026-05-18T00:00:29.244274+00:00"},{"alias_kind":"pith_short_12","alias_value":"H4FGSMKYRM5M","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"H4FGSMKYRM5M3YBP","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"H4FGSMKY","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"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":46,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13472","citing_title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q","json":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q.json","graph_json":"https://pith.science/api/pith-number/H4FGSMKYRM5M3YBPYIQXBLHO3Q/graph.json","events_json":"https://pith.science/api/pith-number/H4FGSMKYRM5M3YBPYIQXBLHO3Q/events.json","paper":"https://pith.science/paper/H4FGSMKY"},"agent_actions":{"view_html":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q","download_json":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q.json","view_paper":"https://pith.science/paper/H4FGSMKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.07029&json=true","fetch_graph":"https://pith.science/api/pith-number/H4FGSMKYRM5M3YBPYIQXBLHO3Q/graph.json","fetch_events":"https://pith.science/api/pith-number/H4FGSMKYRM5M3YBPYIQXBLHO3Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q/action/storage_attestation","attest_author":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q/action/author_attestation","sign_citation":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q/action/citation_signature","submit_replication":"https://pith.science/pith/H4FGSMKYRM5M3YBPYIQXBLHO3Q/action/replication_record"}},"created_at":"2026-05-18T00:00:29.244274+00:00","updated_at":"2026-05-18T00:00:29.244274+00:00"}