{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ICKKFKWUMWDDW4IGZMU733Z7UN","short_pith_number":"pith:ICKKFKWU","schema_version":"1.0","canonical_sha256":"4094a2aad465863b7106cb29fdef3fa34db46dfc57922907862513dcdd388138","source":{"kind":"arxiv","id":"1810.06394","version":1},"attestation_state":"computed","paper":{"title":"Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Liu, Haobo Fu, Jiechao Xiong, Ji Liu, Lei Han, Peng Sun, Qing Wang, Tong Zhang, Yang Zheng, Zhuoran Yang","submitted_at":"2018-10-10T07:38:44Z","abstract_excerpt":"Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely. Motivated by applications in computer games, we consider the scenario with discrete-continuous hybrid action space. To handle hybrid action space, previous works either approximate the hybrid space by discretization, or relax it into a continuous set. In this paper, we propose a parametrized deep Q-network (P- DQN) framework for the hybrid action space without approximation or relaxation. Our algorithm combines the spirits of both DQN (dealing with discrete action"},"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":"1810.06394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T07:38:44Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6da7d5867bf2a2a12a9b6238222522480f3b9a85cbf967dbfeea09b2e325600d","abstract_canon_sha256":"2962987c8682b5d1ada8726bc5849491f23799d3c3020846a87227d5acee7fcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:20.613543Z","signature_b64":"Arm+gyP30DJkWEfY2jI3HvLRgI1L8e4wla66qM44Y3eLkjC8Hemg97C6bC+J37b6FDbrgsu9klLYXlh5N4SGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4094a2aad465863b7106cb29fdef3fa34db46dfc57922907862513dcdd388138","last_reissued_at":"2026-05-18T00:03:20.612981Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:20.612981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Han Liu, Haobo Fu, Jiechao Xiong, Ji Liu, Lei Han, Peng Sun, Qing Wang, Tong Zhang, Yang Zheng, Zhuoran Yang","submitted_at":"2018-10-10T07:38:44Z","abstract_excerpt":"Most existing deep reinforcement learning (DRL) frameworks consider either discrete action space or continuous action space solely. Motivated by applications in computer games, we consider the scenario with discrete-continuous hybrid action space. To handle hybrid action space, previous works either approximate the hybrid space by discretization, or relax it into a continuous set. In this paper, we propose a parametrized deep Q-network (P- DQN) framework for the hybrid action space without approximation or relaxation. Our algorithm combines the spirits of both DQN (dealing with discrete action"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06394","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":"1810.06394","created_at":"2026-05-18T00:03:20.613058+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.06394v1","created_at":"2026-05-18T00:03:20.613058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06394","created_at":"2026-05-18T00:03:20.613058+00:00"},{"alias_kind":"pith_short_12","alias_value":"ICKKFKWUMWDD","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"ICKKFKWUMWDDW4IG","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"ICKKFKWU","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":103,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27118","citing_title":"PALCAS: A Priority-Aware Intelligent Lane Change Advisory System for Autonomous Vehicles using Federated Reinforcement Learning","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN","json":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN.json","graph_json":"https://pith.science/api/pith-number/ICKKFKWUMWDDW4IGZMU733Z7UN/graph.json","events_json":"https://pith.science/api/pith-number/ICKKFKWUMWDDW4IGZMU733Z7UN/events.json","paper":"https://pith.science/paper/ICKKFKWU"},"agent_actions":{"view_html":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN","download_json":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN.json","view_paper":"https://pith.science/paper/ICKKFKWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.06394&json=true","fetch_graph":"https://pith.science/api/pith-number/ICKKFKWUMWDDW4IGZMU733Z7UN/graph.json","fetch_events":"https://pith.science/api/pith-number/ICKKFKWUMWDDW4IGZMU733Z7UN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN/action/storage_attestation","attest_author":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN/action/author_attestation","sign_citation":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN/action/citation_signature","submit_replication":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN/action/replication_record"}},"created_at":"2026-05-18T00:03:20.613058+00:00","updated_at":"2026-05-18T00:03:20.613058+00:00"}