{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VPMLMKW76KYNIPDNBYVUFCANOQ","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":"680b9994004583d5cfce682c8aad644c5b97f0bb13b786f35e6f7a787fdbf66a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T14:42:45Z","title_canon_sha256":"a84e8555ae5cbd0aeaf38038407e36d5fa17045490356d1b699002af9935514b"},"schema_version":"1.0","source":{"id":"2402.03055","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03055","created_at":"2026-07-05T11:56:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03055v5","created_at":"2026-07-05T11:56:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03055","created_at":"2026-07-05T11:56:13Z"},{"alias_kind":"pith_short_12","alias_value":"VPMLMKW76KYN","created_at":"2026-07-05T11:56:13Z"},{"alias_kind":"pith_short_16","alias_value":"VPMLMKW76KYNIPDN","created_at":"2026-07-05T11:56:13Z"},{"alias_kind":"pith_short_8","alias_value":"VPMLMKW7","created_at":"2026-07-05T11:56:13Z"}],"graph_snapshots":[{"event_id":"sha256:52bc28afd9695c0b4a9051569b8a294e1ca8173ed138fdc124110c728cf2b6ce","target":"graph","created_at":"2026-07-05T11:56:13Z","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/2402.03055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) for continuous control under delayed rewards is an under-explored problem despite its significance in real-world applications. Many complex skills are based on intermediate ones as prerequisites. For instance, a humanoid locomotor must learn how to stand before it can learn to walk. To cope with delayed reward, an agent must perform deep exploration. However, existing deep exploration methods are designed for small discrete action spaces, and their generalization to state-of-the-art continuous control remains unproven. We address the deep exploration problem for the","authors_text":"Bahareh Tasdighi, Manuel Haussmann, Melih Kandemir, Nicklas Werge, Yi-Shan Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T14:42:45Z","title":"Deep Exploration with PAC-Bayes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03055","kind":"arxiv","version":5},"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:b06641be26548927fce80e5d4673bc9e7f2aa483cf51caa02d64570bd746b22f","target":"record","created_at":"2026-07-05T11:56:13Z","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":"680b9994004583d5cfce682c8aad644c5b97f0bb13b786f35e6f7a787fdbf66a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-05T14:42:45Z","title_canon_sha256":"a84e8555ae5cbd0aeaf38038407e36d5fa17045490356d1b699002af9935514b"},"schema_version":"1.0","source":{"id":"2402.03055","kind":"arxiv","version":5}},"canonical_sha256":"abd8b62adff2b0d43c6d0e2b42880d740c8ac99db5895f287394866a566d4f7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abd8b62adff2b0d43c6d0e2b42880d740c8ac99db5895f287394866a566d4f7f","first_computed_at":"2026-07-05T11:56:13.308578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:13.308578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IUtBWkX/alfLOBNabgGFapKkXZ2+9bwiD7Lfx/P5sNmSHLVaD4pLTG9vMEXMODL5/eKnpT9l12VFg9mhz2+cAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:13.309062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.03055","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b06641be26548927fce80e5d4673bc9e7f2aa483cf51caa02d64570bd746b22f","sha256:52bc28afd9695c0b4a9051569b8a294e1ca8173ed138fdc124110c728cf2b6ce"],"state_sha256":"084100bacd5a5c815becbf41e03b4b4cdb64bbdb1425a75794824b9c4444d014"}