{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XBV5XLCLS5Y4QF6I4WWTR335MW","short_pith_number":"pith:XBV5XLCL","schema_version":"1.0","canonical_sha256":"b86bdbac4b9771c817c8e5ad38ef7d659d13a35476ce9daf88b57ea73298eb65","source":{"kind":"arxiv","id":"1905.04388","version":1},"attestation_state":"computed","paper":{"title":"Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Craig J. Bester, George D. Konidaris, Steven D. James","submitted_at":"2019-05-10T21:57:41Z","abstract_excerpt":"Parameterised actions in reinforcement learning are composed of discrete actions with continuous action-parameters. This provides a framework for solving complex domains that require combining high-level actions with flexible control. The recent P-DQN algorithm extends deep Q-networks to learn over such action spaces. However, it treats all action-parameters as a single joint input to the Q-network, invalidating its theoretical foundations. We analyse the issues with this approach and propose a novel method, multi-pass deep Q-networks, or MP-DQN, to address them. We empirically demonstrate tha"},"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":"1905.04388","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T21:57:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e6db6a89616c222a10351a7cd02d29faf0e30ce521a3ff5a14558aca32506ea8","abstract_canon_sha256":"6e357e4d297d20500140f21a8786d1acf0ca3105baa3b82f57997acbb26d6eb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:25.104937Z","signature_b64":"BLbr4jV9/Jh0fm9CZrrWxZ2+c1/HOuQzjbMfcNvDNBakkNmtkCVuaP/uLBiBIh4tkRdsQT4G+bhtoq5/J2ITCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b86bdbac4b9771c817c8e5ad38ef7d659d13a35476ce9daf88b57ea73298eb65","last_reissued_at":"2026-05-17T23:46:25.104277Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:25.104277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Craig J. Bester, George D. Konidaris, Steven D. James","submitted_at":"2019-05-10T21:57:41Z","abstract_excerpt":"Parameterised actions in reinforcement learning are composed of discrete actions with continuous action-parameters. This provides a framework for solving complex domains that require combining high-level actions with flexible control. The recent P-DQN algorithm extends deep Q-networks to learn over such action spaces. However, it treats all action-parameters as a single joint input to the Q-network, invalidating its theoretical foundations. We analyse the issues with this approach and propose a novel method, multi-pass deep Q-networks, or MP-DQN, to address them. We empirically demonstrate tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04388","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":"1905.04388","created_at":"2026-05-17T23:46:25.104396+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.04388v1","created_at":"2026-05-17T23:46:25.104396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04388","created_at":"2026-05-17T23:46:25.104396+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBV5XLCLS5Y4","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBV5XLCLS5Y4QF6I","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBV5XLCL","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.20831","citing_title":"Context-Sensitive Abstractions for Reinforcement Learning with Parameterized Actions","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19677","citing_title":"Learning Hybrid-Control Policies for High-Precision In-Contact Manipulation Under Uncertainty","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBV5XLCLS5Y4QF6I4WWTR335MW","json":"https://pith.science/pith/XBV5XLCLS5Y4QF6I4WWTR335MW.json","graph_json":"https://pith.science/api/pith-number/XBV5XLCLS5Y4QF6I4WWTR335MW/graph.json","events_json":"https://pith.science/api/pith-number/XBV5XLCLS5Y4QF6I4WWTR335MW/events.json","paper":"https://pith.science/paper/XBV5XLCL"},"agent_actions":{"view_html":"https://pith.science/pith/XBV5XLCLS5Y4QF6I4WWTR335MW","download_json":"https://pith.science/pith/XBV5XLCLS5Y4QF6I4WWTR335MW.json","view_paper":"https://pith.science/paper/XBV5XLCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.04388&json=true","fetch_graph":"https://pith.science/api/pith-number/XBV5XLCLS5Y4QF6I4WWTR335MW/graph.json","fetch_events":"https://pith.science/api/pith-number/XBV5XLCLS5Y4QF6I4WWTR335MW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBV5XLCLS5Y4QF6I4WWTR335MW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBV5XLCLS5Y4QF6I4WWTR335MW/action/storage_attestation","attest_author":"https://pith.science/pith/XBV5XLCLS5Y4QF6I4WWTR335MW/action/author_attestation","sign_citation":"https://pith.science/pith/XBV5XLCLS5Y4QF6I4WWTR335MW/action/citation_signature","submit_replication":"https://pith.science/pith/XBV5XLCLS5Y4QF6I4WWTR335MW/action/replication_record"}},"created_at":"2026-05-17T23:46:25.104396+00:00","updated_at":"2026-05-17T23:46:25.104396+00:00"}