{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EMGLXVFFRZ4M2HS2CMKQALLBGF","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":"4a86b6d5c810226807888156c16052584420800f1e746249700d03bc47c663ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T09:38:21Z","title_canon_sha256":"aebe0633c5f860bbf97cc1e6d00f6901dea6a95b16b2b370e6bd7f4f5d899cee"},"schema_version":"1.0","source":{"id":"2505.11044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11044","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11044v1","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11044","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_12","alias_value":"EMGLXVFFRZ4M","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_16","alias_value":"EMGLXVFFRZ4M2HS2","created_at":"2026-07-05T11:04:09Z"},{"alias_kind":"pith_short_8","alias_value":"EMGLXVFF","created_at":"2026-07-05T11:04:09Z"}],"graph_snapshots":[{"event_id":"sha256:db8125f3a7ee262eb2e8d76e824ed7fea2e9315a2deaf74f6c6738e7803a618c","target":"graph","created_at":"2026-07-05T11:04:09Z","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/2505.11044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration remains a critical challenge in online reinforcement learning, as an agent must effectively explore unknown environments to achieve high returns. Currently, the main exploration algorithms are primarily count-based methods and curiosity-based methods, with prediction-error methods being a prominent example. In this paper, we propose a novel method called \\textbf{R}andom \\textbf{D}istribution \\textbf{D}istillation (RDD), which samples the output of a target network from a normal distribution. RDD facilitates a more extensive exploration by explicitly treating the difference between ","authors_text":"Jiafei Lyu, Jian Tao, Kai Yang, Li Shen, Lusong Li, Xiu Li, Zhirui Fang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T09:38:21Z","title":"Exploration by Random Distribution Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11044","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":"sha256:7385eaad0eb9d63a04bdc7cc01f7de1a220ee2860d62c6ab8817eda84cd61d79","target":"record","created_at":"2026-07-05T11:04:09Z","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":"4a86b6d5c810226807888156c16052584420800f1e746249700d03bc47c663ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T09:38:21Z","title_canon_sha256":"aebe0633c5f860bbf97cc1e6d00f6901dea6a95b16b2b370e6bd7f4f5d899cee"},"schema_version":"1.0","source":{"id":"2505.11044","kind":"arxiv","version":1}},"canonical_sha256":"230cbbd4a58e78cd1e5a1315002d61315bf480ea4492f25564ce5b26c2e7c6cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"230cbbd4a58e78cd1e5a1315002d61315bf480ea4492f25564ce5b26c2e7c6cb","first_computed_at":"2026-07-05T11:04:09.808699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:09.808699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C6WufyVK1VrgLKwrT3iYfFdQOmSWkgYWMLlha5tLzP7ErzTq3a2C63fuil9kZ8MmdE77f6gUmPkedH8rV0l7Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:09.809152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7385eaad0eb9d63a04bdc7cc01f7de1a220ee2860d62c6ab8817eda84cd61d79","sha256:db8125f3a7ee262eb2e8d76e824ed7fea2e9315a2deaf74f6c6738e7803a618c"],"state_sha256":"61b765c2a933f3a1f3f6c9c84441438d9cbeddb588341622d26d2f1917d1b263"}