{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XESYBCRATBDVURGBCVT223CVPV","short_pith_number":"pith:XESYBCRA","schema_version":"1.0","canonical_sha256":"b925808a2098475a44c11567ad6c557d715889bf066708455ecac0710f429756","source":{"kind":"arxiv","id":"2208.07914","version":3},"attestation_state":"computed","paper":{"title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Suat Gumussoy, Toygun Basaklar, Umit Y. Ogras","submitted_at":"2022-08-16T19:23:02Z","abstract_excerpt":"Multi-objective reinforcement learning (MORL) approaches have emerged to tackle many real-world problems with multiple conflicting objectives by maximizing a joint objective function weighted by a preference vector. These approaches find fixed customized policies corresponding to preference vectors specified during training. However, the design constraints and objectives typically change dynamically in real-life scenarios. Furthermore, storing a policy for each potential preference is not scalable. Hence, obtaining a set of Pareto front solutions for the entire preference space in a given doma"},"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":"2208.07914","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-16T19:23:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8581c8db545f923c37e9c1a122abe7824236c8d595e46235cd0ae528be55f12b","abstract_canon_sha256":"94e89f0306108b21090ec7e957b50b97de7ec95dad661bf3339bb2cfdd4b1e8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:56.355187Z","signature_b64":"T8+aNQc4L2brpQXMyNAwYCthy74YBAxiI+26UVWT/VUgV7FjgGIXIojzb/PdguUdtnXS6XNuVD0DQBLUpTC4DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b925808a2098475a44c11567ad6c557d715889bf066708455ecac0710f429756","last_reissued_at":"2026-07-05T06:14:56.354660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:56.354660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Suat Gumussoy, Toygun Basaklar, Umit Y. Ogras","submitted_at":"2022-08-16T19:23:02Z","abstract_excerpt":"Multi-objective reinforcement learning (MORL) approaches have emerged to tackle many real-world problems with multiple conflicting objectives by maximizing a joint objective function weighted by a preference vector. These approaches find fixed customized policies corresponding to preference vectors specified during training. However, the design constraints and objectives typically change dynamically in real-life scenarios. Furthermore, storing a policy for each potential preference is not scalable. Hence, obtaining a set of Pareto front solutions for the entire preference space in a given doma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.07914","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2208.07914/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2208.07914","created_at":"2026-07-05T06:14:56.354730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.07914v3","created_at":"2026-07-05T06:14:56.354730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.07914","created_at":"2026-07-05T06:14:56.354730+00:00"},{"alias_kind":"pith_short_12","alias_value":"XESYBCRATBDV","created_at":"2026-07-05T06:14:56.354730+00:00"},{"alias_kind":"pith_short_16","alias_value":"XESYBCRATBDVURGB","created_at":"2026-07-05T06:14:56.354730+00:00"},{"alias_kind":"pith_short_8","alias_value":"XESYBCRA","created_at":"2026-07-05T06:14:56.354730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21943","citing_title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08946","citing_title":"A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XESYBCRATBDVURGBCVT223CVPV","json":"https://pith.science/pith/XESYBCRATBDVURGBCVT223CVPV.json","graph_json":"https://pith.science/api/pith-number/XESYBCRATBDVURGBCVT223CVPV/graph.json","events_json":"https://pith.science/api/pith-number/XESYBCRATBDVURGBCVT223CVPV/events.json","paper":"https://pith.science/paper/XESYBCRA"},"agent_actions":{"view_html":"https://pith.science/pith/XESYBCRATBDVURGBCVT223CVPV","download_json":"https://pith.science/pith/XESYBCRATBDVURGBCVT223CVPV.json","view_paper":"https://pith.science/paper/XESYBCRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.07914&json=true","fetch_graph":"https://pith.science/api/pith-number/XESYBCRATBDVURGBCVT223CVPV/graph.json","fetch_events":"https://pith.science/api/pith-number/XESYBCRATBDVURGBCVT223CVPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XESYBCRATBDVURGBCVT223CVPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XESYBCRATBDVURGBCVT223CVPV/action/storage_attestation","attest_author":"https://pith.science/pith/XESYBCRATBDVURGBCVT223CVPV/action/author_attestation","sign_citation":"https://pith.science/pith/XESYBCRATBDVURGBCVT223CVPV/action/citation_signature","submit_replication":"https://pith.science/pith/XESYBCRATBDVURGBCVT223CVPV/action/replication_record"}},"created_at":"2026-07-05T06:14:56.354730+00:00","updated_at":"2026-07-05T06:14:56.354730+00:00"}