{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ICKKFKWUMWDDW4IGZMU733Z7UN","short_pith_number":"pith:ICKKFKWU","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"},"canonical_sha256":"4094a2aad465863b7106cb29fdef3fa34db46dfc57922907862513dcdd388138","source":{"kind":"arxiv","id":"1810.06394","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06394","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06394v1","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06394","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"ICKKFKWUMWDD","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"ICKKFKWUMWDDW4IG","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"ICKKFKWU","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ICKKFKWUMWDDW4IGZMU733Z7UN","target":"record","payload":{"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"},"canonical_sha256":"4094a2aad465863b7106cb29fdef3fa34db46dfc57922907862513dcdd388138","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"},"source_kind":"arxiv","source_id":"1810.06394","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":"2026-05-18T00:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"io8KCaeA35D2Pfci6WbyGu0oibvZ0IhuJyvUt7tdBPbEWhXlGIt9s157+cFCX3FnnIhaGG05a87MqaGVC+XYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T23:46:29.656753Z"},"content_sha256":"07b5cbe3c622cc86259cd08fb0ebf87d0f4af496cb720b45cd03b474aa05d3b1","schema_version":"1.0","event_id":"sha256:07b5cbe3c622cc86259cd08fb0ebf87d0f4af496cb720b45cd03b474aa05d3b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ICKKFKWUMWDDW4IGZMU733Z7UN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:03:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5dWMF5Vdm0X0yEFe3RA8jyOLOOo4mqnAhbxUoypx4jd/1pgG+WgHC7baII+siBl7ArDbUJve0OrOWOo70f+pCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T23:46:29.657103Z"},"content_sha256":"55c7035b951cf54c2ae284ccd61231da989ed0d3265f1371f9cecd26a062d55e","schema_version":"1.0","event_id":"sha256:55c7035b951cf54c2ae284ccd61231da989ed0d3265f1371f9cecd26a062d55e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN/bundle.json","state_url":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICKKFKWUMWDDW4IGZMU733Z7UN/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":"2026-06-01T23:46:29Z","links":{"resolver":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN","bundle":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN/bundle.json","state":"https://pith.science/pith/ICKKFKWUMWDDW4IGZMU733Z7UN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICKKFKWUMWDDW4IGZMU733Z7UN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ICKKFKWUMWDDW4IGZMU733Z7UN","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":"2962987c8682b5d1ada8726bc5849491f23799d3c3020846a87227d5acee7fcd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T07:38:44Z","title_canon_sha256":"6da7d5867bf2a2a12a9b6238222522480f3b9a85cbf967dbfeea09b2e325600d"},"schema_version":"1.0","source":{"id":"1810.06394","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.06394","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"arxiv_version","alias_value":"1810.06394v1","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.06394","created_at":"2026-05-18T00:03:20Z"},{"alias_kind":"pith_short_12","alias_value":"ICKKFKWUMWDD","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"ICKKFKWUMWDDW4IG","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"ICKKFKWU","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:55c7035b951cf54c2ae284ccd61231da989ed0d3265f1371f9cecd26a062d55e","target":"graph","created_at":"2026-05-18T00:03:20Z","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":"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","authors_text":"Han Liu, Haobo Fu, Jiechao Xiong, Ji Liu, Lei Han, Peng Sun, Qing Wang, Tong Zhang, Yang Zheng, Zhuoran Yang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T07:38:44Z","title":"Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.06394","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":"sha256:07b5cbe3c622cc86259cd08fb0ebf87d0f4af496cb720b45cd03b474aa05d3b1","target":"record","created_at":"2026-05-18T00:03:20Z","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":"2962987c8682b5d1ada8726bc5849491f23799d3c3020846a87227d5acee7fcd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-10T07:38:44Z","title_canon_sha256":"6da7d5867bf2a2a12a9b6238222522480f3b9a85cbf967dbfeea09b2e325600d"},"schema_version":"1.0","source":{"id":"1810.06394","kind":"arxiv","version":1}},"canonical_sha256":"4094a2aad465863b7106cb29fdef3fa34db46dfc57922907862513dcdd388138","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4094a2aad465863b7106cb29fdef3fa34db46dfc57922907862513dcdd388138","first_computed_at":"2026-05-18T00:03:20.612981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:20.612981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Arm+gyP30DJkWEfY2jI3HvLRgI1L8e4wla66qM44Y3eLkjC8Hemg97C6bC+J37b6FDbrgsu9klLYXlh5N4SGDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:20.613543Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.06394","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07b5cbe3c622cc86259cd08fb0ebf87d0f4af496cb720b45cd03b474aa05d3b1","sha256:55c7035b951cf54c2ae284ccd61231da989ed0d3265f1371f9cecd26a062d55e"],"state_sha256":"afb0cbc27f1ce6d67969700c955ca28a14c7b40c4f1e2ab81142df027f9390ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pMdq1vblX9KR30xsKsu9xGbiRIwpOgscE9xdpoq7830XGCXm/cTN9LowK3DBLbuh1efjTsaOqzKQ9udHWGDuBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T23:46:29.659029Z","bundle_sha256":"23b6df3896619b6c80c41aed690f1538e15a00633d5cff89d15d634175db407f"}}