{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XBV5XLCLS5Y4QF6I4WWTR335MW","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":"6e357e4d297d20500140f21a8786d1acf0ca3105baa3b82f57997acbb26d6eb3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T21:57:41Z","title_canon_sha256":"e6db6a89616c222a10351a7cd02d29faf0e30ce521a3ff5a14558aca32506ea8"},"schema_version":"1.0","source":{"id":"1905.04388","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.04388","created_at":"2026-05-17T23:46:25Z"},{"alias_kind":"arxiv_version","alias_value":"1905.04388v1","created_at":"2026-05-17T23:46:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04388","created_at":"2026-05-17T23:46:25Z"},{"alias_kind":"pith_short_12","alias_value":"XBV5XLCLS5Y4","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XBV5XLCLS5Y4QF6I","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XBV5XLCL","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:154a3010638e83ec4f3ef265b8e52164e8833e927556557a83744bb26220ea8b","target":"graph","created_at":"2026-05-17T23:46:25Z","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":"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","authors_text":"Craig J. Bester, George D. Konidaris, Steven D. James","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T21:57:41Z","title":"Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04388","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":"sha256:13126d4a51597ba430cd770c4948c4f6181a56caaba6b430621cd2de2192c732","target":"record","created_at":"2026-05-17T23:46:25Z","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":"6e357e4d297d20500140f21a8786d1acf0ca3105baa3b82f57997acbb26d6eb3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-10T21:57:41Z","title_canon_sha256":"e6db6a89616c222a10351a7cd02d29faf0e30ce521a3ff5a14558aca32506ea8"},"schema_version":"1.0","source":{"id":"1905.04388","kind":"arxiv","version":1}},"canonical_sha256":"b86bdbac4b9771c817c8e5ad38ef7d659d13a35476ce9daf88b57ea73298eb65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b86bdbac4b9771c817c8e5ad38ef7d659d13a35476ce9daf88b57ea73298eb65","first_computed_at":"2026-05-17T23:46:25.104277Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:25.104277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BLbr4jV9/Jh0fm9CZrrWxZ2+c1/HOuQzjbMfcNvDNBakkNmtkCVuaP/uLBiBIh4tkRdsQT4G+bhtoq5/J2ITCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:25.104937Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.04388","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13126d4a51597ba430cd770c4948c4f6181a56caaba6b430621cd2de2192c732","sha256:154a3010638e83ec4f3ef265b8e52164e8833e927556557a83744bb26220ea8b"],"state_sha256":"61c40644411e25a72431d81a6ad5a6fd59285c09a7c00f709ecf344e97fdaf30"}