{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2N2DMZRLT7ZINZ5NB2K37CIEJ5","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":"f6ed7d4c1932cb4519151401a8c706619c470f8f889a7ce13fb202f35665c4c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T12:34:00Z","title_canon_sha256":"c80b53668d1db31b030ecba6cfb8314de1862a3bafe52a5e65299b79746e4428"},"schema_version":"1.0","source":{"id":"2506.08737","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08737","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08737v1","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08737","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"pith_short_12","alias_value":"2N2DMZRLT7ZI","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"pith_short_16","alias_value":"2N2DMZRLT7ZINZ5N","created_at":"2026-07-05T11:19:12Z"},{"alias_kind":"pith_short_8","alias_value":"2N2DMZRL","created_at":"2026-07-05T11:19:12Z"}],"graph_snapshots":[{"event_id":"sha256:14fdf3438baeb05ce2441858750bcda722eec38da9b101298ceaa357dca14e8b","target":"graph","created_at":"2026-07-05T11:19:12Z","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/2506.08737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Random Reward Perturbation (RRP), a novel exploration strategy for reinforcement learning (RL). Our theoretical analyses demonstrate that adding zero-mean noise to environmental rewards effectively enhances policy diversity during training, thereby expanding the range of exploration. RRP is fully compatible with the action-perturbation-based exploration strategies, such as $\\epsilon$-greedy, stochastic policies, and entropy regularization, providing additive improvements to exploration effects. It is general, lightweight, and can be integrated into existing RL algorithms with mini","authors_text":"Guoji Fu, Haozhe Ma, Jiele Wu, Tze-Yun Leong, Zhengding Luo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T12:34:00Z","title":"Exploration by Random Reward Perturbation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08737","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":"sha256:9c5d0efcb7289f10f24895bc3716a9f2a0d678ca90a7412f79b9741b9dfec3c3","target":"record","created_at":"2026-07-05T11:19:12Z","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":"f6ed7d4c1932cb4519151401a8c706619c470f8f889a7ce13fb202f35665c4c4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T12:34:00Z","title_canon_sha256":"c80b53668d1db31b030ecba6cfb8314de1862a3bafe52a5e65299b79746e4428"},"schema_version":"1.0","source":{"id":"2506.08737","kind":"arxiv","version":1}},"canonical_sha256":"d37436662b9ff286e7ad0e95bf89044f6d335927bf43e0e646358cac5e62d640","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d37436662b9ff286e7ad0e95bf89044f6d335927bf43e0e646358cac5e62d640","first_computed_at":"2026-07-05T11:19:12.447220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:12.447220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dWUdGlJj+U66K/SsCjUqupWwkXkata5H3/FWSoO8EZD/rRaGHjAhHvOgSRn2mJEdM8juK8DA7ePgeqV1RAdfCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:12.447692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08737","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c5d0efcb7289f10f24895bc3716a9f2a0d678ca90a7412f79b9741b9dfec3c3","sha256:14fdf3438baeb05ce2441858750bcda722eec38da9b101298ceaa357dca14e8b"],"state_sha256":"1e2e6a399add6fd751c1ab36d71785efd9a74bc7d55ebb7c6506a23d4c674d29"}