{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TNJ6H6Y4KIK55WXLWKEOWM2OUV","short_pith_number":"pith:TNJ6H6Y4","schema_version":"1.0","canonical_sha256":"9b53e3fb1c5215dedaebb288eb334ea54f746e4386a6446d65a0c54dd0e29e26","source":{"kind":"arxiv","id":"2310.16487","version":1},"attestation_state":"computed","paper":{"title":"Hyperparameter Optimization for Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Gareev, El-Ghazali Talbi, Florian Felten, Gr\\'egoire Danoy","submitted_at":"2023-10-25T09:17:25Z","abstract_excerpt":"Reinforcement learning (RL) has emerged as a powerful approach for tackling complex problems. The recent introduction of multi-objective reinforcement learning (MORL) has further expanded the scope of RL by enabling agents to make trade-offs among multiple objectives. This advancement not only has broadened the range of problems that can be tackled but also created numerous opportunities for exploration and advancement. Yet, the effectiveness of RL agents heavily relies on appropriately setting their hyperparameters. In practice, this task often proves to be challenging, leading to unsuccessfu"},"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":"2310.16487","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-25T09:17:25Z","cross_cats_sorted":[],"title_canon_sha256":"26763ec6326aae20a782665ea81d49d5fe39f983a049c3c59871b4248ed79519","abstract_canon_sha256":"72e4043061d07a203852063da6c3358250fa483a10fb4f3fcaa9f33c9368d2aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:58.239027Z","signature_b64":"R8RiNb79B4I8mAUYi9aclMifHGQUq/Ummn0xrx9JI2dORdiUb+qxU+VddlSfyHpP26Mkz06Yel3JuYnuZqHMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b53e3fb1c5215dedaebb288eb334ea54f746e4386a6446d65a0c54dd0e29e26","last_reissued_at":"2026-07-05T07:04:58.238575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:58.238575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hyperparameter Optimization for Multi-Objective Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Gareev, El-Ghazali Talbi, Florian Felten, Gr\\'egoire Danoy","submitted_at":"2023-10-25T09:17:25Z","abstract_excerpt":"Reinforcement learning (RL) has emerged as a powerful approach for tackling complex problems. The recent introduction of multi-objective reinforcement learning (MORL) has further expanded the scope of RL by enabling agents to make trade-offs among multiple objectives. This advancement not only has broadened the range of problems that can be tackled but also created numerous opportunities for exploration and advancement. Yet, the effectiveness of RL agents heavily relies on appropriately setting their hyperparameters. In practice, this task often proves to be challenging, leading to unsuccessfu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16487","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.16487/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":"2310.16487","created_at":"2026-07-05T07:04:58.238636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16487v1","created_at":"2026-07-05T07:04:58.238636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16487","created_at":"2026-07-05T07:04:58.238636+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNJ6H6Y4KIK5","created_at":"2026-07-05T07:04:58.238636+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNJ6H6Y4KIK55WXL","created_at":"2026-07-05T07:04:58.238636+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNJ6H6Y4","created_at":"2026-07-05T07:04:58.238636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.00831","citing_title":"EngiBench: A Framework for Data-Driven Engineering Design Research","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNJ6H6Y4KIK55WXLWKEOWM2OUV","json":"https://pith.science/pith/TNJ6H6Y4KIK55WXLWKEOWM2OUV.json","graph_json":"https://pith.science/api/pith-number/TNJ6H6Y4KIK55WXLWKEOWM2OUV/graph.json","events_json":"https://pith.science/api/pith-number/TNJ6H6Y4KIK55WXLWKEOWM2OUV/events.json","paper":"https://pith.science/paper/TNJ6H6Y4"},"agent_actions":{"view_html":"https://pith.science/pith/TNJ6H6Y4KIK55WXLWKEOWM2OUV","download_json":"https://pith.science/pith/TNJ6H6Y4KIK55WXLWKEOWM2OUV.json","view_paper":"https://pith.science/paper/TNJ6H6Y4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16487&json=true","fetch_graph":"https://pith.science/api/pith-number/TNJ6H6Y4KIK55WXLWKEOWM2OUV/graph.json","fetch_events":"https://pith.science/api/pith-number/TNJ6H6Y4KIK55WXLWKEOWM2OUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNJ6H6Y4KIK55WXLWKEOWM2OUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNJ6H6Y4KIK55WXLWKEOWM2OUV/action/storage_attestation","attest_author":"https://pith.science/pith/TNJ6H6Y4KIK55WXLWKEOWM2OUV/action/author_attestation","sign_citation":"https://pith.science/pith/TNJ6H6Y4KIK55WXLWKEOWM2OUV/action/citation_signature","submit_replication":"https://pith.science/pith/TNJ6H6Y4KIK55WXLWKEOWM2OUV/action/replication_record"}},"created_at":"2026-07-05T07:04:58.238636+00:00","updated_at":"2026-07-05T07:04:58.238636+00:00"}