{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NWYDPC4NACNFAMJOF6MGPSFUVY","short_pith_number":"pith:NWYDPC4N","schema_version":"1.0","canonical_sha256":"6db0378b8d009a50312e2f9867c8b4ae28b667505f323bd1a5cbd692c709cac9","source":{"kind":"arxiv","id":"2508.01329","version":1},"attestation_state":"computed","paper":{"title":"Is Exploration or Optimization the Problem for Deep Reinforcement Learning?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Glen Berseth","submitted_at":"2025-08-02T11:40:26Z","abstract_excerpt":"In the era of deep reinforcement learning, making progress is more complex, as the collected experience must be compressed into a deep model for future exploitation and sampling. Many papers have shown that training a deep learning policy under the changing state and action distribution leads to sub-optimal performance, or even collapse. This naturally leads to the concern that even if the community creates improved exploration algorithms or reward objectives, will those improvements fall on the \\textit{deaf ears} of optimization difficulties. This work proposes a new \\textit{practical} sub-op"},"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":"2508.01329","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-02T11:40:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc81f8f62d6201f509e1a05d56570c5a249a45d55c8ed790aea19bcaef6747de","abstract_canon_sha256":"d6bfb816b7b3f32675193bd64df4e30223c722fc774503e5b8f99ebe8fb7a4e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:37.466685Z","signature_b64":"E8RAjvhH3q5CL+Lu2kEDoOrtc/HxqPbwxwmgi7jVKv0hKKxt0PWaXs01ZM53c76ISFGbPALQeT+OnoXXtZqyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6db0378b8d009a50312e2f9867c8b4ae28b667505f323bd1a5cbd692c709cac9","last_reissued_at":"2026-07-05T11:47:37.466217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:37.466217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Exploration or Optimization the Problem for Deep Reinforcement Learning?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Glen Berseth","submitted_at":"2025-08-02T11:40:26Z","abstract_excerpt":"In the era of deep reinforcement learning, making progress is more complex, as the collected experience must be compressed into a deep model for future exploitation and sampling. Many papers have shown that training a deep learning policy under the changing state and action distribution leads to sub-optimal performance, or even collapse. This naturally leads to the concern that even if the community creates improved exploration algorithms or reward objectives, will those improvements fall on the \\textit{deaf ears} of optimization difficulties. This work proposes a new \\textit{practical} sub-op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01329","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/2508.01329/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":"2508.01329","created_at":"2026-07-05T11:47:37.466280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.01329v1","created_at":"2026-07-05T11:47:37.466280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01329","created_at":"2026-07-05T11:47:37.466280+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWYDPC4NACNF","created_at":"2026-07-05T11:47:37.466280+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWYDPC4NACNFAMJO","created_at":"2026-07-05T11:47:37.466280+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWYDPC4N","created_at":"2026-07-05T11:47:37.466280+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/NWYDPC4NACNFAMJOF6MGPSFUVY","json":"https://pith.science/pith/NWYDPC4NACNFAMJOF6MGPSFUVY.json","graph_json":"https://pith.science/api/pith-number/NWYDPC4NACNFAMJOF6MGPSFUVY/graph.json","events_json":"https://pith.science/api/pith-number/NWYDPC4NACNFAMJOF6MGPSFUVY/events.json","paper":"https://pith.science/paper/NWYDPC4N"},"agent_actions":{"view_html":"https://pith.science/pith/NWYDPC4NACNFAMJOF6MGPSFUVY","download_json":"https://pith.science/pith/NWYDPC4NACNFAMJOF6MGPSFUVY.json","view_paper":"https://pith.science/paper/NWYDPC4N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.01329&json=true","fetch_graph":"https://pith.science/api/pith-number/NWYDPC4NACNFAMJOF6MGPSFUVY/graph.json","fetch_events":"https://pith.science/api/pith-number/NWYDPC4NACNFAMJOF6MGPSFUVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWYDPC4NACNFAMJOF6MGPSFUVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWYDPC4NACNFAMJOF6MGPSFUVY/action/storage_attestation","attest_author":"https://pith.science/pith/NWYDPC4NACNFAMJOF6MGPSFUVY/action/author_attestation","sign_citation":"https://pith.science/pith/NWYDPC4NACNFAMJOF6MGPSFUVY/action/citation_signature","submit_replication":"https://pith.science/pith/NWYDPC4NACNFAMJOF6MGPSFUVY/action/replication_record"}},"created_at":"2026-07-05T11:47:37.466280+00:00","updated_at":"2026-07-05T11:47:37.466280+00:00"}