{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UCK5PQ4KBLS4AB7RFWTSWDY6LL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ef2e2888d322001e81bed557befeab642fa92165beb360667121efa467cd3098","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-30T15:54:18Z","title_canon_sha256":"477d6b4fd065f7a62561ae32c7d72a1fffc99279d2444d43dba7f3021315f679"},"schema_version":"1.0","source":{"id":"2407.20917","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.20917","created_at":"2026-07-05T08:50:20Z"},{"alias_kind":"arxiv_version","alias_value":"2407.20917v1","created_at":"2026-07-05T08:50:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.20917","created_at":"2026-07-05T08:50:20Z"},{"alias_kind":"pith_short_12","alias_value":"UCK5PQ4KBLS4","created_at":"2026-07-05T08:50:20Z"},{"alias_kind":"pith_short_16","alias_value":"UCK5PQ4KBLS4AB7R","created_at":"2026-07-05T08:50:20Z"},{"alias_kind":"pith_short_8","alias_value":"UCK5PQ4K","created_at":"2026-07-05T08:50:20Z"}],"graph_snapshots":[{"event_id":"sha256:8338556144c5ee1ba455bd4fe010689e6baa5b14a60624e95bcad3d086e210d9","target":"graph","created_at":"2026-07-05T08:50:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.20917/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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/.","authors_text":"Daniel Cremers, Fabian Bongratz, Felix Czaja, Frederik Heetmeyer, Julian Rodemann, Luca Della Libera, Lukas Mautner, Vladimir Golkov","cross_cats":["cs.AI","cs.CV","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-30T15:54:18Z","title":"How to Choose a Reinforcement-Learning Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.20917","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b91c06de605c2392409330c6ebae9c2ea555edc783fdcbd6bdbf47b5f622e96e","target":"record","created_at":"2026-07-05T08:50:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ef2e2888d322001e81bed557befeab642fa92165beb360667121efa467cd3098","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-30T15:54:18Z","title_canon_sha256":"477d6b4fd065f7a62561ae32c7d72a1fffc99279d2444d43dba7f3021315f679"},"schema_version":"1.0","source":{"id":"2407.20917","kind":"arxiv","version":1}},"canonical_sha256":"a095d7c38a0ae5c007f12da72b0f1e5affd04ee272cd39707f654af557ab152c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a095d7c38a0ae5c007f12da72b0f1e5affd04ee272cd39707f654af557ab152c","first_computed_at":"2026-07-05T08:50:20.458405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:20.458405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qqQ4VIeqgBGMAxBd7rrSvnR72PcaHfjO6FOxKwHBaKfI34rH2JpAAzwOe6wdepnYrjO5r/hmitZpl4zZJBWUDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:20.458938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.20917","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b91c06de605c2392409330c6ebae9c2ea555edc783fdcbd6bdbf47b5f622e96e","sha256:8338556144c5ee1ba455bd4fe010689e6baa5b14a60624e95bcad3d086e210d9"],"state_sha256":"5c538602c0a0b82110c2a6b80ab0aca6189cb0ca45b2b2483c943729b485b28e"}