{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UCK5PQ4KBLS4AB7RFWTSWDY6LL","short_pith_number":"pith:UCK5PQ4K","schema_version":"1.0","canonical_sha256":"a095d7c38a0ae5c007f12da72b0f1e5affd04ee272cd39707f654af557ab152c","source":{"kind":"arxiv","id":"2407.20917","version":1},"attestation_state":"computed","paper":{"title":"How to Choose a Reinforcement-Learning Algorithm","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Cremers, Fabian Bongratz, Felix Czaja, Frederik Heetmeyer, Julian Rodemann, Luca Della Libera, Lukas Mautner, Vladimir Golkov","submitted_at":"2024-07-30T15:54:18Z","abstract_excerpt":"The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods. An interactive version of these guidelines is available online at https://rl-picker.github.io/."},"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":"2407.20917","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-30T15:54:18Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"477d6b4fd065f7a62561ae32c7d72a1fffc99279d2444d43dba7f3021315f679","abstract_canon_sha256":"ef2e2888d322001e81bed557befeab642fa92165beb360667121efa467cd3098"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:20.458938Z","signature_b64":"qqQ4VIeqgBGMAxBd7rrSvnR72PcaHfjO6FOxKwHBaKfI34rH2JpAAzwOe6wdepnYrjO5r/hmitZpl4zZJBWUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a095d7c38a0ae5c007f12da72b0f1e5affd04ee272cd39707f654af557ab152c","last_reissued_at":"2026-07-05T08:50:20.458405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:20.458405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Choose a Reinforcement-Learning Algorithm","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Cremers, Fabian Bongratz, Felix Czaja, Frederik Heetmeyer, Julian Rodemann, Luca Della Libera, Lukas Mautner, Vladimir Golkov","submitted_at":"2024-07-30T15:54:18Z","abstract_excerpt":"The field of reinforcement learning offers a large variety of concepts and methods to tackle sequential decision-making problems. This variety has become so large that choosing an algorithm for a task at hand can be challenging. In this work, we streamline the process of choosing reinforcement-learning algorithms and action-distribution families. We provide a structured overview of existing methods and their properties, as well as guidelines for when to choose which methods. An interactive version of these guidelines is available online at https://rl-picker.github.io/."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20917","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/2407.20917/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":"2407.20917","created_at":"2026-07-05T08:50:20.458464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.20917v1","created_at":"2026-07-05T08:50:20.458464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20917","created_at":"2026-07-05T08:50:20.458464+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCK5PQ4KBLS4","created_at":"2026-07-05T08:50:20.458464+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCK5PQ4KBLS4AB7R","created_at":"2026-07-05T08:50:20.458464+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCK5PQ4K","created_at":"2026-07-05T08:50:20.458464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UCK5PQ4KBLS4AB7RFWTSWDY6LL","json":"https://pith.science/pith/UCK5PQ4KBLS4AB7RFWTSWDY6LL.json","graph_json":"https://pith.science/api/pith-number/UCK5PQ4KBLS4AB7RFWTSWDY6LL/graph.json","events_json":"https://pith.science/api/pith-number/UCK5PQ4KBLS4AB7RFWTSWDY6LL/events.json","paper":"https://pith.science/paper/UCK5PQ4K"},"agent_actions":{"view_html":"https://pith.science/pith/UCK5PQ4KBLS4AB7RFWTSWDY6LL","download_json":"https://pith.science/pith/UCK5PQ4KBLS4AB7RFWTSWDY6LL.json","view_paper":"https://pith.science/paper/UCK5PQ4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.20917&json=true","fetch_graph":"https://pith.science/api/pith-number/UCK5PQ4KBLS4AB7RFWTSWDY6LL/graph.json","fetch_events":"https://pith.science/api/pith-number/UCK5PQ4KBLS4AB7RFWTSWDY6LL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCK5PQ4KBLS4AB7RFWTSWDY6LL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCK5PQ4KBLS4AB7RFWTSWDY6LL/action/storage_attestation","attest_author":"https://pith.science/pith/UCK5PQ4KBLS4AB7RFWTSWDY6LL/action/author_attestation","sign_citation":"https://pith.science/pith/UCK5PQ4KBLS4AB7RFWTSWDY6LL/action/citation_signature","submit_replication":"https://pith.science/pith/UCK5PQ4KBLS4AB7RFWTSWDY6LL/action/replication_record"}},"created_at":"2026-07-05T08:50:20.458464+00:00","updated_at":"2026-07-05T08:50:20.458464+00:00"}