{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6W57RBK54SDJU7UWIWGPGU32IO","short_pith_number":"pith:6W57RBK5","canonical_record":{"source":{"id":"1809.07803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T18:52:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ecf9eb7634bbb3e19e9a94ab58b2642eda8dfdef7e9ad66256d3014473a3e5d6","abstract_canon_sha256":"ddff50f5a5a4087cdab4921dd659b6e95bc6f701e8a93e89d822a5144d8f3b92"},"schema_version":"1.0"},"canonical_sha256":"f5bbf8855de4869a7e96458cf3537a43bda5011e043496aca5412fa02e46deae","source":{"kind":"arxiv","id":"1809.07803","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.07803","created_at":"2026-05-17T23:46:29Z"},{"alias_kind":"arxiv_version","alias_value":"1809.07803v2","created_at":"2026-05-17T23:46:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07803","created_at":"2026-05-17T23:46:29Z"},{"alias_kind":"pith_short_12","alias_value":"6W57RBK54SDJ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6W57RBK54SDJU7UW","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6W57RBK5","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6W57RBK54SDJU7UWIWGPGU32IO","target":"record","payload":{"canonical_record":{"source":{"id":"1809.07803","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T18:52:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ecf9eb7634bbb3e19e9a94ab58b2642eda8dfdef7e9ad66256d3014473a3e5d6","abstract_canon_sha256":"ddff50f5a5a4087cdab4921dd659b6e95bc6f701e8a93e89d822a5144d8f3b92"},"schema_version":"1.0"},"canonical_sha256":"f5bbf8855de4869a7e96458cf3537a43bda5011e043496aca5412fa02e46deae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:29.933795Z","signature_b64":"0DzqTgVoEkFCkMu/Hp/nm1xI8XEoLnSbMfn31g0708WK9J3On6aca+WXJCJGDgwe6LRmLxrJBhHzxCgsUR5SCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5bbf8855de4869a7e96458cf3537a43bda5011e043496aca5412fa02e46deae","last_reissued_at":"2026-05-17T23:46:29.933075Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:29.933075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.07803","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0EI/oTKIHGSXBBiGks1MQI4SZl4sxX1UDj9TwonGDJBIKBxyeWKIf39QowIDPpea0YeeN/Own2TTr74sIMZBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T12:24:36.727298Z"},"content_sha256":"22f914ef7539f223b47ca4399eb8fb13f1f38cce125374956fa5174c924f230c","schema_version":"1.0","event_id":"sha256:22f914ef7539f223b47ca4399eb8fb13f1f38cce125374956fa5174c924f230c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6W57RBK54SDJU7UWIWGPGU32IO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Weights in Multi-Objective Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ann Now\\'e, Axel Abels, Denis Steckelmacher, Diederik M. Roijers, Tom Lenaerts","submitted_at":"2018-09-20T18:52:15Z","abstract_excerpt":"Many real-world decision problems are characterized by multiple conflicting objectives which must be balanced based on their relative importance. In the dynamic weights setting the relative importance changes over time and specialized algorithms that deal with such change, such as a tabular Reinforcement Learning (RL) algorithm by Natarajan and Tadepalli (2005), are required. However, this earlier work is not feasible for RL settings that necessitate the use of function approximators. We generalize across weight changes and high-dimensional inputs by proposing a multi-objective Q-network whose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07803","kind":"arxiv","version":2},"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":"2026-05-17T23:46:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0LLW/7U1vVIIhjTDpRxpmKqcNHQQdem+EpddrNhPLZ223e3Nhk4rfXXAKHGKd166HmfLAXi/cvf7jrtbUc6NAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T12:24:36.727969Z"},"content_sha256":"b15f9066cd380b416822545e1e3bd1303e60784f1856171ba7daed7c91b88fe4","schema_version":"1.0","event_id":"sha256:b15f9066cd380b416822545e1e3bd1303e60784f1856171ba7daed7c91b88fe4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6W57RBK54SDJU7UWIWGPGU32IO/bundle.json","state_url":"https://pith.science/pith/6W57RBK54SDJU7UWIWGPGU32IO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6W57RBK54SDJU7UWIWGPGU32IO/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":"2026-05-27T12:24:36Z","links":{"resolver":"https://pith.science/pith/6W57RBK54SDJU7UWIWGPGU32IO","bundle":"https://pith.science/pith/6W57RBK54SDJU7UWIWGPGU32IO/bundle.json","state":"https://pith.science/pith/6W57RBK54SDJU7UWIWGPGU32IO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6W57RBK54SDJU7UWIWGPGU32IO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6W57RBK54SDJU7UWIWGPGU32IO","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":"ddff50f5a5a4087cdab4921dd659b6e95bc6f701e8a93e89d822a5144d8f3b92","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T18:52:15Z","title_canon_sha256":"ecf9eb7634bbb3e19e9a94ab58b2642eda8dfdef7e9ad66256d3014473a3e5d6"},"schema_version":"1.0","source":{"id":"1809.07803","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.07803","created_at":"2026-05-17T23:46:29Z"},{"alias_kind":"arxiv_version","alias_value":"1809.07803v2","created_at":"2026-05-17T23:46:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.07803","created_at":"2026-05-17T23:46:29Z"},{"alias_kind":"pith_short_12","alias_value":"6W57RBK54SDJ","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6W57RBK54SDJU7UW","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6W57RBK5","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:b15f9066cd380b416822545e1e3bd1303e60784f1856171ba7daed7c91b88fe4","target":"graph","created_at":"2026-05-17T23:46:29Z","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":"Many real-world decision problems are characterized by multiple conflicting objectives which must be balanced based on their relative importance. In the dynamic weights setting the relative importance changes over time and specialized algorithms that deal with such change, such as a tabular Reinforcement Learning (RL) algorithm by Natarajan and Tadepalli (2005), are required. However, this earlier work is not feasible for RL settings that necessitate the use of function approximators. We generalize across weight changes and high-dimensional inputs by proposing a multi-objective Q-network whose","authors_text":"Ann Now\\'e, Axel Abels, Denis Steckelmacher, Diederik M. Roijers, Tom Lenaerts","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T18:52:15Z","title":"Dynamic Weights in Multi-Objective Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.07803","kind":"arxiv","version":2},"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":"sha256:22f914ef7539f223b47ca4399eb8fb13f1f38cce125374956fa5174c924f230c","target":"record","created_at":"2026-05-17T23:46:29Z","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":"ddff50f5a5a4087cdab4921dd659b6e95bc6f701e8a93e89d822a5144d8f3b92","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-20T18:52:15Z","title_canon_sha256":"ecf9eb7634bbb3e19e9a94ab58b2642eda8dfdef7e9ad66256d3014473a3e5d6"},"schema_version":"1.0","source":{"id":"1809.07803","kind":"arxiv","version":2}},"canonical_sha256":"f5bbf8855de4869a7e96458cf3537a43bda5011e043496aca5412fa02e46deae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5bbf8855de4869a7e96458cf3537a43bda5011e043496aca5412fa02e46deae","first_computed_at":"2026-05-17T23:46:29.933075Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:29.933075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0DzqTgVoEkFCkMu/Hp/nm1xI8XEoLnSbMfn31g0708WK9J3On6aca+WXJCJGDgwe6LRmLxrJBhHzxCgsUR5SCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:29.933795Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.07803","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22f914ef7539f223b47ca4399eb8fb13f1f38cce125374956fa5174c924f230c","sha256:b15f9066cd380b416822545e1e3bd1303e60784f1856171ba7daed7c91b88fe4"],"state_sha256":"85f8a1b8fe0ce4fa58cbe184b3557f5d0263ddaecc3dccc15a6e3357b8b1fe86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fw6mjHKS5tAJulvvQTW6gDAnX1zRUipUmlTCF0KldJbKOioTRfUN6XggC7dEcU931HbWDecoTEZ+pR38JnELBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T12:24:36.731517Z","bundle_sha256":"147b7313f3a6d93982e4e62cf89ae3107fb66cdb28ffefb14ed1c78d525c3636"}}