{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U4CMGOZCHOFQJ5B4MZ5AHYRIMH","short_pith_number":"pith:U4CMGOZC","schema_version":"1.0","canonical_sha256":"a704c33b223b8b04f43c667a03e22861c8bbcc28d2251aacd385fd51a7b266fc","source":{"kind":"arxiv","id":"2103.09568","version":1},"attestation_state":"computed","paper":{"title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ann Now\\'e, Athirai A. Irissappane, Conor F. Hayes, Diederik M. Roijers, Enda Howley, Eugenio Bargiacchi, Fredrik Heintz, Gabriel Ramos, Johan K\\\"allstr\\\"om, Luisa M. Zintgraf, Marcello Restelli, Mathieu Reymond, Matthew Macfarlane, Patrick Mannion, Peter Vamplew, Richard Dazeley, Roxana R\\u{a}dulescu, Timothy Verstraeten","submitted_at":"2021-03-17T11:07:28Z","abstract_excerpt":"Real-world decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcement learning and decision-theoretic planning either assumes only a single objective, or that multiple objectives can be adequately handled via a simple linear combination. Such approaches may oversimplify the underlying problem and hence produce suboptimal results. This paper serves as a guide to the application of multi-objective methods to difficult problems, and is aimed at researchers who are already familiar with "},"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":"2103.09568","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-03-17T11:07:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"12fe327efe57b5f4e78851a80c5cb128bd91c0e18057b266c46553ee10d6090e","abstract_canon_sha256":"5ac953ea83b62e65128571956aeb18824e8d0494ce3ed69f98e65c7339f90e4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:35.348159Z","signature_b64":"TsKCDV8X6LsQfreXnlitS/wpF2DXL0sNaAO3oGTDqoWjECT79nWAsMJXlrpjIRbb8kRvq7qqqGTjVC4meDWtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a704c33b223b8b04f43c667a03e22861c8bbcc28d2251aacd385fd51a7b266fc","last_reissued_at":"2026-07-05T04:16:35.347647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:35.347647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ann Now\\'e, Athirai A. Irissappane, Conor F. Hayes, Diederik M. Roijers, Enda Howley, Eugenio Bargiacchi, Fredrik Heintz, Gabriel Ramos, Johan K\\\"allstr\\\"om, Luisa M. Zintgraf, Marcello Restelli, Mathieu Reymond, Matthew Macfarlane, Patrick Mannion, Peter Vamplew, Richard Dazeley, Roxana R\\u{a}dulescu, Timothy Verstraeten","submitted_at":"2021-03-17T11:07:28Z","abstract_excerpt":"Real-world decision-making tasks are generally complex, requiring trade-offs between multiple, often conflicting, objectives. Despite this, the majority of research in reinforcement learning and decision-theoretic planning either assumes only a single objective, or that multiple objectives can be adequately handled via a simple linear combination. Such approaches may oversimplify the underlying problem and hence produce suboptimal results. This paper serves as a guide to the application of multi-objective methods to difficult problems, and is aimed at researchers who are already familiar with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09568","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/2103.09568/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":"2103.09568","created_at":"2026-07-05T04:16:35.347713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09568v1","created_at":"2026-07-05T04:16:35.347713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09568","created_at":"2026-07-05T04:16:35.347713+00:00"},{"alias_kind":"pith_short_12","alias_value":"U4CMGOZCHOFQ","created_at":"2026-07-05T04:16:35.347713+00:00"},{"alias_kind":"pith_short_16","alias_value":"U4CMGOZCHOFQJ5B4","created_at":"2026-07-05T04:16:35.347713+00:00"},{"alias_kind":"pith_short_8","alias_value":"U4CMGOZC","created_at":"2026-07-05T04:16:35.347713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00642","citing_title":"Coachable agents for interactive gameplay","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30893","citing_title":"Sampling-Based Coordination-Informed Multi-Objective Multi-Robot Reinforcement Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31178","citing_title":"AETDICE: Unified Framework and Offline Optimization for Nonlinear Multi-Objective RL","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16344","citing_title":"A Production-Ready RL Framework for Personalized Utility Tuning with Pareto Sweeping in Pinterest Recommender Systems","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13647","citing_title":"FlowCompile: An Optimizing Compiler for Structured LLM Workflows","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12771","citing_title":"Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08946","citing_title":"A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U4CMGOZCHOFQJ5B4MZ5AHYRIMH","json":"https://pith.science/pith/U4CMGOZCHOFQJ5B4MZ5AHYRIMH.json","graph_json":"https://pith.science/api/pith-number/U4CMGOZCHOFQJ5B4MZ5AHYRIMH/graph.json","events_json":"https://pith.science/api/pith-number/U4CMGOZCHOFQJ5B4MZ5AHYRIMH/events.json","paper":"https://pith.science/paper/U4CMGOZC"},"agent_actions":{"view_html":"https://pith.science/pith/U4CMGOZCHOFQJ5B4MZ5AHYRIMH","download_json":"https://pith.science/pith/U4CMGOZCHOFQJ5B4MZ5AHYRIMH.json","view_paper":"https://pith.science/paper/U4CMGOZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09568&json=true","fetch_graph":"https://pith.science/api/pith-number/U4CMGOZCHOFQJ5B4MZ5AHYRIMH/graph.json","fetch_events":"https://pith.science/api/pith-number/U4CMGOZCHOFQJ5B4MZ5AHYRIMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U4CMGOZCHOFQJ5B4MZ5AHYRIMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U4CMGOZCHOFQJ5B4MZ5AHYRIMH/action/storage_attestation","attest_author":"https://pith.science/pith/U4CMGOZCHOFQJ5B4MZ5AHYRIMH/action/author_attestation","sign_citation":"https://pith.science/pith/U4CMGOZCHOFQJ5B4MZ5AHYRIMH/action/citation_signature","submit_replication":"https://pith.science/pith/U4CMGOZCHOFQJ5B4MZ5AHYRIMH/action/replication_record"}},"created_at":"2026-07-05T04:16:35.347713+00:00","updated_at":"2026-07-05T04:16:35.347713+00:00"}