{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZWDOH2GW4BHYBQDSNX7HFA3MMY","short_pith_number":"pith:ZWDOH2GW","schema_version":"1.0","canonical_sha256":"cd86e3e8d6e04f80c0726dfe72836c660e92f55c61013fad1f4b0444052ff19f","source":{"kind":"arxiv","id":"1903.04959","version":1},"attestation_state":"computed","paper":{"title":"Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Changjie Fan, Haotian Fu, Hongyao Tang, Jianye Hao, Yingfeng Chen, Zihan Lei","submitted_at":"2019-03-12T14:40:32Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) has been applied to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces. However, to the best of our knowledge, no previous work has ever succeeded in applying DRL to multi-agent problems with discrete-continuous hybrid (or parameterized) action spaces which is very common in practice. Our work fills this gap by proposing two novel algorithms: Deep Multi-Agent Parameterized Q-Networks (Deep MAPQN) and Deep Multi-Agent Hierarchical Hybrid Q-Networks (Deep MAHHQN). We follow the centralized trainin"},"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":"1903.04959","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-12T14:40:32Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"d8abfa2534aa128e0724b43f5bd3095848dc7b759b04e63762ae867b7f0688e8","abstract_canon_sha256":"2930babf32a84106636402254bc6fd2df1fb00ce1a811051e5279395c9a302b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:29.021778Z","signature_b64":"WLAqgDePEoJLlC9CQXPZ8RwzHS6xgAQdCbRcuNj6sJYTLB4SZ039l4vh5h9L/woBokqO0G74TnhCTBEVIb7AAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd86e3e8d6e04f80c0726dfe72836c660e92f55c61013fad1f4b0444052ff19f","last_reissued_at":"2026-05-17T23:44:29.021083Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:29.021083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Changjie Fan, Haotian Fu, Hongyao Tang, Jianye Hao, Yingfeng Chen, Zihan Lei","submitted_at":"2019-03-12T14:40:32Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) has been applied to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces. However, to the best of our knowledge, no previous work has ever succeeded in applying DRL to multi-agent problems with discrete-continuous hybrid (or parameterized) action spaces which is very common in practice. Our work fills this gap by proposing two novel algorithms: Deep Multi-Agent Parameterized Q-Networks (Deep MAPQN) and Deep Multi-Agent Hierarchical Hybrid Q-Networks (Deep MAHHQN). We follow the centralized trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04959","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":"1903.04959","created_at":"2026-05-17T23:44:29.021199+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.04959v1","created_at":"2026-05-17T23:44:29.021199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04959","created_at":"2026-05-17T23:44:29.021199+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWDOH2GW4BHY","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWDOH2GW4BHYBQDS","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWDOH2GW","created_at":"2026-05-18T12:33:33.725879+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/ZWDOH2GW4BHYBQDSNX7HFA3MMY","json":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY.json","graph_json":"https://pith.science/api/pith-number/ZWDOH2GW4BHYBQDSNX7HFA3MMY/graph.json","events_json":"https://pith.science/api/pith-number/ZWDOH2GW4BHYBQDSNX7HFA3MMY/events.json","paper":"https://pith.science/paper/ZWDOH2GW"},"agent_actions":{"view_html":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY","download_json":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY.json","view_paper":"https://pith.science/paper/ZWDOH2GW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.04959&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWDOH2GW4BHYBQDSNX7HFA3MMY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWDOH2GW4BHYBQDSNX7HFA3MMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY/action/storage_attestation","attest_author":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY/action/author_attestation","sign_citation":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY/action/citation_signature","submit_replication":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY/action/replication_record"}},"created_at":"2026-05-17T23:44:29.021199+00:00","updated_at":"2026-05-17T23:44:29.021199+00:00"}