{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:327AZAHVZILCZOSMCVOA3BCL7S","short_pith_number":"pith:327AZAHV","schema_version":"1.0","canonical_sha256":"debe0c80f5ca162cba4c155c0d844bfc9b2ec8e0221c5629266727a903b1e978","source":{"kind":"arxiv","id":"2402.01361","version":2},"attestation_state":"computed","paper":{"title":"To the Max: Reinventing Reward in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Grigorii Veviurko, Mathijs de Weerdt, Wendelin B\\\"ohmer","submitted_at":"2024-02-02T12:29:18Z","abstract_excerpt":"In reinforcement learning (RL), different reward functions can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stuck with a suboptimal behavior, and for others, it solves the task efficiently. Choosing a good reward function is hence an extremely important yet challenging problem. In this paper, we explore an alternative approach for using rewards for learning. We introduce \\textit{max-reward RL}, where an agent optimizes the maximum rather than the cumulative reward. Unlike earlier works, our approach works for deterministic an"},"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":"2402.01361","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T12:29:18Z","cross_cats_sorted":[],"title_canon_sha256":"a48e6f05e7db7f0b0994b1afaf89c2100c8f73f5358094578a04e5c41039013c","abstract_canon_sha256":"a4f82ab98267fac5e025ce1e206ed71dd0c7895c7246dd47a656ec77efe7780a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:34.776533Z","signature_b64":"uPOYiHJIeqvLKPv60omUsBYWYBK4Wl0/yruQ96HcoThkeFhcsn0ZeNs1oiX1aZbnThZj/+2GFNhccPcsrBLoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"debe0c80f5ca162cba4c155c0d844bfc9b2ec8e0221c5629266727a903b1e978","last_reissued_at":"2026-07-05T10:18:34.776087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:34.776087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"To the Max: Reinventing Reward in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Grigorii Veviurko, Mathijs de Weerdt, Wendelin B\\\"ohmer","submitted_at":"2024-02-02T12:29:18Z","abstract_excerpt":"In reinforcement learning (RL), different reward functions can define the same optimal policy but result in drastically different learning performance. For some, the agent gets stuck with a suboptimal behavior, and for others, it solves the task efficiently. Choosing a good reward function is hence an extremely important yet challenging problem. In this paper, we explore an alternative approach for using rewards for learning. We introduce \\textit{max-reward RL}, where an agent optimizes the maximum rather than the cumulative reward. Unlike earlier works, our approach works for deterministic an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01361","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.01361/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":"2402.01361","created_at":"2026-07-05T10:18:34.776143+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01361v2","created_at":"2026-07-05T10:18:34.776143+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01361","created_at":"2026-07-05T10:18:34.776143+00:00"},{"alias_kind":"pith_short_12","alias_value":"327AZAHVZILC","created_at":"2026-07-05T10:18:34.776143+00:00"},{"alias_kind":"pith_short_16","alias_value":"327AZAHVZILCZOSM","created_at":"2026-07-05T10:18:34.776143+00:00"},{"alias_kind":"pith_short_8","alias_value":"327AZAHV","created_at":"2026-07-05T10:18:34.776143+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18531","citing_title":"When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15788","citing_title":"ADAPT: A Self-Calibrating Proactive Autoscaler for Container Orchestration","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S","json":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S.json","graph_json":"https://pith.science/api/pith-number/327AZAHVZILCZOSMCVOA3BCL7S/graph.json","events_json":"https://pith.science/api/pith-number/327AZAHVZILCZOSMCVOA3BCL7S/events.json","paper":"https://pith.science/paper/327AZAHV"},"agent_actions":{"view_html":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S","download_json":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S.json","view_paper":"https://pith.science/paper/327AZAHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01361&json=true","fetch_graph":"https://pith.science/api/pith-number/327AZAHVZILCZOSMCVOA3BCL7S/graph.json","fetch_events":"https://pith.science/api/pith-number/327AZAHVZILCZOSMCVOA3BCL7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S/action/storage_attestation","attest_author":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S/action/author_attestation","sign_citation":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S/action/citation_signature","submit_replication":"https://pith.science/pith/327AZAHVZILCZOSMCVOA3BCL7S/action/replication_record"}},"created_at":"2026-07-05T10:18:34.776143+00:00","updated_at":"2026-07-05T10:18:34.776143+00:00"}