{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2V46SO7A6YAS3KL26UNI2ES64H","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":"12d86a7f665fe147f0d8835cfc1ef8cf00f78e778fb80ae3db8699bf38711317","cross_cats_sorted":["cs.AI","cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T19:47:34Z","title_canon_sha256":"864dfab83910c4e7af64af7e4ad2c9d6cdeb73faf65d19fd8e3a730d58da5bbf"},"schema_version":"1.0","source":{"id":"2402.06023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.06023","created_at":"2026-07-05T07:43:17Z"},{"alias_kind":"arxiv_version","alias_value":"2402.06023v1","created_at":"2026-07-05T07:43:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06023","created_at":"2026-07-05T07:43:17Z"},{"alias_kind":"pith_short_12","alias_value":"2V46SO7A6YAS","created_at":"2026-07-05T07:43:17Z"},{"alias_kind":"pith_short_16","alias_value":"2V46SO7A6YAS3KL2","created_at":"2026-07-05T07:43:17Z"},{"alias_kind":"pith_short_8","alias_value":"2V46SO7A","created_at":"2026-07-05T07:43:17Z"}],"graph_snapshots":[{"event_id":"sha256:0052d11410397604574920e50915e75cb3a4ac70ef6e8798b0ba741d160b0204","target":"graph","created_at":"2026-07-05T07:43:17Z","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/2402.06023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces a novel approach, Decision Theory-guided Deep Reinforcement Learning (DT-guided DRL), to address the inherent cold start problem in DRL. By integrating decision theory principles, DT-guided DRL enhances agents' initial performance and robustness in complex environments, enabling more efficient and reliable convergence during learning. Our investigation encompasses two primary problem contexts: the cart pole and maze navigation challenges. Experimental results demonstrate that the integration of decision theory not only facilitates effective initial guidance for DRL agents","authors_text":"Ahmed H. Anwar, Charles Kamhoua, Jin-Hee Cho, Munindar P. Singh, Mu Zhu, Zelin Wan","cross_cats":["cs.AI","cs.GT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T19:47:34Z","title":"Decision Theory-Guided Deep Reinforcement Learning for Fast Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06023","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:bc8c3a33c4afdd5e08956fdaba6977693f01dba02c39ca1b7118821bb0035ac0","target":"record","created_at":"2026-07-05T07:43:17Z","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":"12d86a7f665fe147f0d8835cfc1ef8cf00f78e778fb80ae3db8699bf38711317","cross_cats_sorted":["cs.AI","cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T19:47:34Z","title_canon_sha256":"864dfab83910c4e7af64af7e4ad2c9d6cdeb73faf65d19fd8e3a730d58da5bbf"},"schema_version":"1.0","source":{"id":"2402.06023","kind":"arxiv","version":1}},"canonical_sha256":"d579e93be0f6012da97af51a8d125ee1fa5d04830f4c922353d85c68fae3caca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d579e93be0f6012da97af51a8d125ee1fa5d04830f4c922353d85c68fae3caca","first_computed_at":"2026-07-05T07:43:17.033838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:17.033838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y8ZlddsQALKRCYyZhgm3Jx6PUhc5/oysvjr9dctZpQSUVJodl+4qXuyZmfJSs4u6WY2VUPZzeJVfvyzW0qEzDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:17.034326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.06023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc8c3a33c4afdd5e08956fdaba6977693f01dba02c39ca1b7118821bb0035ac0","sha256:0052d11410397604574920e50915e75cb3a4ac70ef6e8798b0ba741d160b0204"],"state_sha256":"675a6e377fba7a9e95fc1b77516623d94459a0e397f850385628fe820b790a61"}