{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZWDOH2GW4BHYBQDSNX7HFA3MMY","short_pith_number":"pith:ZWDOH2GW","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"},"canonical_sha256":"cd86e3e8d6e04f80c0726dfe72836c660e92f55c61013fad1f4b0444052ff19f","source":{"kind":"arxiv","id":"1903.04959","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.04959","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"arxiv_version","alias_value":"1903.04959v1","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04959","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"pith_short_12","alias_value":"ZWDOH2GW4BHY","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZWDOH2GW4BHYBQDS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZWDOH2GW","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZWDOH2GW4BHYBQDSNX7HFA3MMY","target":"record","payload":{"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"},"canonical_sha256":"cd86e3e8d6e04f80c0726dfe72836c660e92f55c61013fad1f4b0444052ff19f","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"},"source_kind":"arxiv","source_id":"1903.04959","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hadJ2qOYbjifTPpCUO/xQx3cBJO0+cdqamtj2U1dRZhkoXtNFWoqPI7d3FvfpBpOr2bHTrxDKHUKPBYVTgsYBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:39:35.109897Z"},"content_sha256":"833e096c25b93efdceef647b1b9dd0e92224a1ec68d839fd148258d28113e854","schema_version":"1.0","event_id":"sha256:833e096c25b93efdceef647b1b9dd0e92224a1ec68d839fd148258d28113e854"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZWDOH2GW4BHYBQDSNX7HFA3MMY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:44:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UaWZ6lEKohc1AVoKJFfGe9fNYF6dcmm59TJd3otqArTqW0uGEX8u5qSwuKsKx5qWNqUuaD7YGTx+CuzlEJgKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T02:39:35.110591Z"},"content_sha256":"f7abd781962ddd7c9bc724e8fd6c855a31bd846a96aa3ff14650084edc51b66d","schema_version":"1.0","event_id":"sha256:f7abd781962ddd7c9bc724e8fd6c855a31bd846a96aa3ff14650084edc51b66d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY/bundle.json","state_url":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T02:39:35Z","links":{"resolver":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY","bundle":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY/bundle.json","state":"https://pith.science/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZWDOH2GW4BHYBQDSNX7HFA3MMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZWDOH2GW4BHYBQDSNX7HFA3MMY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2930babf32a84106636402254bc6fd2df1fb00ce1a811051e5279395c9a302b9","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-12T14:40:32Z","title_canon_sha256":"d8abfa2534aa128e0724b43f5bd3095848dc7b759b04e63762ae867b7f0688e8"},"schema_version":"1.0","source":{"id":"1903.04959","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.04959","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"arxiv_version","alias_value":"1903.04959v1","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04959","created_at":"2026-05-17T23:44:29Z"},{"alias_kind":"pith_short_12","alias_value":"ZWDOH2GW4BHY","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"ZWDOH2GW4BHYBQDS","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"ZWDOH2GW","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:f7abd781962ddd7c9bc724e8fd6c855a31bd846a96aa3ff14650084edc51b66d","target":"graph","created_at":"2026-05-17T23:44:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Changjie Fan, Haotian Fu, Hongyao Tang, Jianye Hao, Yingfeng Chen, Zihan Lei","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-12T14:40:32Z","title":"Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04959","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:833e096c25b93efdceef647b1b9dd0e92224a1ec68d839fd148258d28113e854","target":"record","created_at":"2026-05-17T23:44:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2930babf32a84106636402254bc6fd2df1fb00ce1a811051e5279395c9a302b9","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-12T14:40:32Z","title_canon_sha256":"d8abfa2534aa128e0724b43f5bd3095848dc7b759b04e63762ae867b7f0688e8"},"schema_version":"1.0","source":{"id":"1903.04959","kind":"arxiv","version":1}},"canonical_sha256":"cd86e3e8d6e04f80c0726dfe72836c660e92f55c61013fad1f4b0444052ff19f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd86e3e8d6e04f80c0726dfe72836c660e92f55c61013fad1f4b0444052ff19f","first_computed_at":"2026-05-17T23:44:29.021083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:29.021083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WLAqgDePEoJLlC9CQXPZ8RwzHS6xgAQdCbRcuNj6sJYTLB4SZ039l4vh5h9L/woBokqO0G74TnhCTBEVIb7AAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:29.021778Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.04959","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:833e096c25b93efdceef647b1b9dd0e92224a1ec68d839fd148258d28113e854","sha256:f7abd781962ddd7c9bc724e8fd6c855a31bd846a96aa3ff14650084edc51b66d"],"state_sha256":"c88529ac106a62b9f78c0b0dfd908f154483112fa40012f3b4c7c8f0b0139996"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XCNM0p//A6UOgPJScTyPzUhmMcBDXJRxQB3Voz45SlLE5vDjuRDFO1Q95j0Cw8aArpiB4hIVkC/Vz1owREe5DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T02:39:35.113657Z","bundle_sha256":"6c0aa50eb97db9bc63d7d0ab66267b6fb6a6cf02ed32effc6e0eca37320ddcb7"}}