{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K6W7OJYMEWFFOUDZHFPGZNECZK","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":"331f547d225c6dbf34051b5a75876bf4f2ca7cf462a04aaccb1254c2f88faed4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T13:06:09Z","title_canon_sha256":"1603022aef9dc19e881e181eff69826d561c6d72ca9fa5de1e8f5ffb46b6280b"},"schema_version":"1.0","source":{"id":"2406.17523","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17523","created_at":"2026-07-05T09:42:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17523v3","created_at":"2026-07-05T09:42:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17523","created_at":"2026-07-05T09:42:15Z"},{"alias_kind":"pith_short_12","alias_value":"K6W7OJYMEWFF","created_at":"2026-07-05T09:42:15Z"},{"alias_kind":"pith_short_16","alias_value":"K6W7OJYMEWFFOUDZ","created_at":"2026-07-05T09:42:15Z"},{"alias_kind":"pith_short_8","alias_value":"K6W7OJYM","created_at":"2026-07-05T09:42:15Z"}],"graph_snapshots":[{"event_id":"sha256:85f53cc343672a6d85f60452afbe14aaf74080225365874a9e3698fe52b1527e","target":"graph","created_at":"2026-07-05T09:42:15Z","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/2406.17523/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (deep RL) has achieved tremendous success on various domains through a combination of algorithmic design and careful selection of hyper-parameters. Algorithmic improvements are often the result of iterative enhancements built upon prior approaches, while hyper-parameter choices are typically inherited from previous methods or fine-tuned specifically for the proposed technique. Despite their crucial impact on performance, hyper-parameter choices are frequently overshadowed by algorithmic advancements. This paper conducts an extensive empirical study focusing on the r","authors_text":"Aaron Courville, Jo\\~ao G.M. Ara\\'ujo, Johan Obando-Ceron, Pablo Samuel Castro","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T13:06:09Z","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17523","kind":"arxiv","version":3},"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":"sha256:54c56ccc8499186a1dfa461c18159c84d0a455e00b7158af4c180bbb7cf37066","target":"record","created_at":"2026-07-05T09:42:15Z","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":"331f547d225c6dbf34051b5a75876bf4f2ca7cf462a04aaccb1254c2f88faed4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-25T13:06:09Z","title_canon_sha256":"1603022aef9dc19e881e181eff69826d561c6d72ca9fa5de1e8f5ffb46b6280b"},"schema_version":"1.0","source":{"id":"2406.17523","kind":"arxiv","version":3}},"canonical_sha256":"57adf7270c258a575079395e6cb482caa6f7bec4f14e93c80eeb80b7e8113925","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57adf7270c258a575079395e6cb482caa6f7bec4f14e93c80eeb80b7e8113925","first_computed_at":"2026-07-05T09:42:15.045828Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:15.045828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8g8t87arb+Onn/LdNVe7EKjq4KqPHymJxSp3VVO/jStdk9PzDBlN3VPkxAEcBY1Ovt/nanltz+jrENFWpGnCAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:15.046376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17523","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54c56ccc8499186a1dfa461c18159c84d0a455e00b7158af4c180bbb7cf37066","sha256:85f53cc343672a6d85f60452afbe14aaf74080225365874a9e3698fe52b1527e"],"state_sha256":"f4e4a8337c4385e3cfb2aa9c6eb23940c595c84e228183166faa0ee939bad579"}