{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JOXX24ORYUTPIBA2TWDWI2WL2F","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":"f8633a724fd248f01c583828bd4a9294594ec2d65d24b35be2d87253757beeac","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-08T04:50:21Z","title_canon_sha256":"fedc023fb01887b3c0115d326c7ca15ac6c67fc3803328fcd266a1774fc28427"},"schema_version":"1.0","source":{"id":"1803.02965","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.02965","created_at":"2026-07-05T01:33:32Z"},{"alias_kind":"arxiv_version","alias_value":"1803.02965v3","created_at":"2026-07-05T01:33:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02965","created_at":"2026-07-05T01:33:32Z"},{"alias_kind":"pith_short_12","alias_value":"JOXX24ORYUTP","created_at":"2026-07-05T01:33:32Z"},{"alias_kind":"pith_short_16","alias_value":"JOXX24ORYUTPIBA2","created_at":"2026-07-05T01:33:32Z"},{"alias_kind":"pith_short_8","alias_value":"JOXX24OR","created_at":"2026-07-05T01:33:32Z"}],"graph_snapshots":[{"event_id":"sha256:867190c934a0defa83c2ce239a4c08d8c32776dffbfa6c7fc54b925f28ace5c9","target":"graph","created_at":"2026-07-05T01:33:32Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1803.02965/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We develop a high-performance MODRL framework that supports both single-policy and multi-policy strategies, as well as both linear and non-linear approaches to action selection. The experimental results on two benchmark problems (two-objective deep sea treasure environment and three-objective Mountain Car problem) indicate that the proposed framework is able to find the Pareto-optimal solutions effectively. The proposed framework is generic and highly modularized, which ","authors_text":"Chee Peng Lim, Ngoc Duy Nguyen, Peter Vamplew, Richard Dazeley, Saeid Nahavandi, Thanh Thi Nguyen","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-08T04:50:21Z","title":"A Multi-Objective Deep Reinforcement Learning Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02965","kind":"arxiv","version":3},"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:c9bf2f811039e52797bb8f7149a0a447f5ceaf64d3cb17f92fbac681905b1f1b","target":"record","created_at":"2026-07-05T01:33:32Z","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":"f8633a724fd248f01c583828bd4a9294594ec2d65d24b35be2d87253757beeac","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-08T04:50:21Z","title_canon_sha256":"fedc023fb01887b3c0115d326c7ca15ac6c67fc3803328fcd266a1774fc28427"},"schema_version":"1.0","source":{"id":"1803.02965","kind":"arxiv","version":3}},"canonical_sha256":"4baf7d71d1c526f4041a9d87646acbd14872d354e6f9c058015d6d9e0cc43eb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4baf7d71d1c526f4041a9d87646acbd14872d354e6f9c058015d6d9e0cc43eb5","first_computed_at":"2026-07-05T01:33:32.525746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:33:32.525746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u/2T8hgEgcR5ZOvh9R1YyrLL3YQqvPFNml77WuUdeU5nlMbko3HslCB5KJhDKWA0+7KzS0lsDimPcH8fValpBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:33:32.526182Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.02965","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9bf2f811039e52797bb8f7149a0a447f5ceaf64d3cb17f92fbac681905b1f1b","sha256:867190c934a0defa83c2ce239a4c08d8c32776dffbfa6c7fc54b925f28ace5c9"],"state_sha256":"fa4c05def8aa39c898aaafbea62db206e7fbffa1fbbea5629aee302797517103"}