{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OOHVKMTUOQUBTQQD2WQBVUIQWH","short_pith_number":"pith:OOHVKMTU","schema_version":"1.0","canonical_sha256":"738f553274742819c203d5a01ad110b1ded6a9b06be973c084588c82b1833d8d","source":{"kind":"arxiv","id":"2009.01555","version":3},"attestation_state":"computed","paper":{"title":"Sample-Efficient Automated Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Biedenkapp, Frank Hutter, Gregor K\\\"ohler, J\\\"org K.H. Franke","submitted_at":"2020-09-03T10:04:06Z","abstract_excerpt":"Despite significant progress in challenging problems across various domains, applying state-of-the-art deep reinforcement learning (RL) algorithms remains challenging due to their sensitivity to the choice of hyperparameters. This sensitivity can partly be attributed to the non-stationarity of the RL problem, potentially requiring different hyperparameter settings at various stages of the learning process. Additionally, in the RL setting, hyperparameter optimization (HPO) requires a large number of environment interactions, hindering the transfer of the successes in RL to real-world applicatio"},"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":"2009.01555","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-03T10:04:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8ed3982c9882338a159fa8bf9cece815d6a9d1a09a53ae92e64391fe4c3e4401","abstract_canon_sha256":"b028229792f7b7d9bb9da5111368b9c43607b77e64f37ec8837386866bc39c17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:23:58.240220Z","signature_b64":"CR29ICacJPibBrcBcgNnI4JJz8oQ1jtWS9Yp1RBx9QFWph5KA7JqlRivbhTceKBdjNkatYgx/PH0yd8o3LavBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"738f553274742819c203d5a01ad110b1ded6a9b06be973c084588c82b1833d8d","last_reissued_at":"2026-07-05T02:23:58.239789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:23:58.239789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-Efficient Automated Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Biedenkapp, Frank Hutter, Gregor K\\\"ohler, J\\\"org K.H. Franke","submitted_at":"2020-09-03T10:04:06Z","abstract_excerpt":"Despite significant progress in challenging problems across various domains, applying state-of-the-art deep reinforcement learning (RL) algorithms remains challenging due to their sensitivity to the choice of hyperparameters. This sensitivity can partly be attributed to the non-stationarity of the RL problem, potentially requiring different hyperparameter settings at various stages of the learning process. Additionally, in the RL setting, hyperparameter optimization (HPO) requires a large number of environment interactions, hindering the transfer of the successes in RL to real-world applicatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.01555","kind":"arxiv","version":3},"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/2009.01555/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":"2009.01555","created_at":"2026-07-05T02:23:58.239848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.01555v3","created_at":"2026-07-05T02:23:58.239848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.01555","created_at":"2026-07-05T02:23:58.239848+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOHVKMTUOQUB","created_at":"2026-07-05T02:23:58.239848+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOHVKMTUOQUBTQQD","created_at":"2026-07-05T02:23:58.239848+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOHVKMTU","created_at":"2026-07-05T02:23:58.239848+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/OOHVKMTUOQUBTQQD2WQBVUIQWH","json":"https://pith.science/pith/OOHVKMTUOQUBTQQD2WQBVUIQWH.json","graph_json":"https://pith.science/api/pith-number/OOHVKMTUOQUBTQQD2WQBVUIQWH/graph.json","events_json":"https://pith.science/api/pith-number/OOHVKMTUOQUBTQQD2WQBVUIQWH/events.json","paper":"https://pith.science/paper/OOHVKMTU"},"agent_actions":{"view_html":"https://pith.science/pith/OOHVKMTUOQUBTQQD2WQBVUIQWH","download_json":"https://pith.science/pith/OOHVKMTUOQUBTQQD2WQBVUIQWH.json","view_paper":"https://pith.science/paper/OOHVKMTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.01555&json=true","fetch_graph":"https://pith.science/api/pith-number/OOHVKMTUOQUBTQQD2WQBVUIQWH/graph.json","fetch_events":"https://pith.science/api/pith-number/OOHVKMTUOQUBTQQD2WQBVUIQWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOHVKMTUOQUBTQQD2WQBVUIQWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOHVKMTUOQUBTQQD2WQBVUIQWH/action/storage_attestation","attest_author":"https://pith.science/pith/OOHVKMTUOQUBTQQD2WQBVUIQWH/action/author_attestation","sign_citation":"https://pith.science/pith/OOHVKMTUOQUBTQQD2WQBVUIQWH/action/citation_signature","submit_replication":"https://pith.science/pith/OOHVKMTUOQUBTQQD2WQBVUIQWH/action/replication_record"}},"created_at":"2026-07-05T02:23:58.239848+00:00","updated_at":"2026-07-05T02:23:58.239848+00:00"}