{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:T6F5R3AOGKORWGMGG3LWNXS7DJ","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":"63591aff490f54991e476d6e380c1b3e009357c28cfc11a55c31397e7fe71a9c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T13:28:30Z","title_canon_sha256":"17960dc5c58d17c8ca78844bcb342c1804f7c2d634c35810e70cff5df1381821"},"schema_version":"1.0","source":{"id":"2209.07288","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.07288","created_at":"2026-07-05T05:07:02Z"},{"alias_kind":"arxiv_version","alias_value":"2209.07288v2","created_at":"2026-07-05T05:07:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.07288","created_at":"2026-07-05T05:07:02Z"},{"alias_kind":"pith_short_12","alias_value":"T6F5R3AOGKOR","created_at":"2026-07-05T05:07:02Z"},{"alias_kind":"pith_short_16","alias_value":"T6F5R3AOGKORWGMG","created_at":"2026-07-05T05:07:02Z"},{"alias_kind":"pith_short_8","alias_value":"T6F5R3AO","created_at":"2026-07-05T05:07:02Z"}],"graph_snapshots":[{"event_id":"sha256:c07a2dd425d8a9825565bb7b747c762bfb25a0cb828bf8004de46d576d405100","target":"graph","created_at":"2026-07-05T05:07:02Z","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/2209.07288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we study the simple yet universally applicable case of reward shaping in value-based Deep Reinforcement Learning (DRL). We show that reward shifting in the form of the linear transformation is equivalent to changing the initialization of the $Q$-function in function approximation. Based on such an equivalence, we bring the key insight that a positive reward shifting leads to conservative exploitation, while a negative reward shifting leads to curiosity-driven exploration. Accordingly, conservative exploitation improves offline RL value estimation, and optimistic value estimation ","authors_text":"Bolei Zhou, Hao Sun, Jian Guo, Lei Han, Rui Yang, Xiaoteng Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T13:28:30Z","title":"Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.07288","kind":"arxiv","version":2},"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":"sha256:0f24cca20e8f51a3c33979de40ff44e4f89653dfbd8326e0eedcb6032e92bd2d","target":"record","created_at":"2026-07-05T05:07:02Z","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":"63591aff490f54991e476d6e380c1b3e009357c28cfc11a55c31397e7fe71a9c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-15T13:28:30Z","title_canon_sha256":"17960dc5c58d17c8ca78844bcb342c1804f7c2d634c35810e70cff5df1381821"},"schema_version":"1.0","source":{"id":"2209.07288","kind":"arxiv","version":2}},"canonical_sha256":"9f8bd8ec0e329d1b198636d766de5f1a600cd36f2fa90d274780a09fcc50b033","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f8bd8ec0e329d1b198636d766de5f1a600cd36f2fa90d274780a09fcc50b033","first_computed_at":"2026-07-05T05:07:02.894199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:02.894199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EWz+8qvvP71iOIMAegd44kpjt7a0lyRGlcmmH6cSddffQ+8EnaCW2Bmc/qqS340Tel1CBp45SF92zYY+SfkaBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:02.894656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.07288","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f24cca20e8f51a3c33979de40ff44e4f89653dfbd8326e0eedcb6032e92bd2d","sha256:c07a2dd425d8a9825565bb7b747c762bfb25a0cb828bf8004de46d576d405100"],"state_sha256":"de4a0be53376d5b3765f86d241256c8d5090b505c3f191ee44f529f2ce8bf74c"}