{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2CFUBTL4VDNHDSONVBMAOUITUH","short_pith_number":"pith:2CFUBTL4","schema_version":"1.0","canonical_sha256":"d08b40cd7ca8da71c9cda858075113a1fa5863cf18d14d93805974be3d25bb88","source":{"kind":"arxiv","id":"1802.01518","version":1},"attestation_state":"computed","paper":{"title":"Guided Policy Exploration for Markov Decision Processes using an Uncertainty-Based Value-of-Information Criterion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Isaac J. Sledge, Jose C. Principe, Matthew S. Emigh","submitted_at":"2018-02-05T17:24:13Z","abstract_excerpt":"Reinforcement learning in environments with many action-state pairs is challenging. At issue is the number of episodes needed to thoroughly search the policy space. Most conventional heuristics address this search problem in a stochastic manner. This can leave large portions of the policy space unvisited during the early training stages. In this paper, we propose an uncertainty-based, information-theoretic approach for performing guided stochastic searches that more effectively cover the policy space. Our approach is based on the value of information, a criterion that provides the optimal trad"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1802.01518","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-05T17:24:13Z","cross_cats_sorted":[],"title_canon_sha256":"4a2b7fa4f3869d5660a395a8e2408d8b5f1c0c920b713349e2593eab108914a0","abstract_canon_sha256":"4929d02d4edd60e7a511c5959bad9b8040727adad1486985c3c1b77a986f793b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:02.286219Z","signature_b64":"aodoz9dGYmGZyn64edG6Zp0X4TxhBnIslpD9Lum+cKkQy1J6UYBP1jii4wJ6oKZF+vxilgZgpVygg/8TspecDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d08b40cd7ca8da71c9cda858075113a1fa5863cf18d14d93805974be3d25bb88","last_reissued_at":"2026-05-18T00:22:02.285616Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:02.285616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guided Policy Exploration for Markov Decision Processes using an Uncertainty-Based Value-of-Information Criterion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Isaac J. Sledge, Jose C. Principe, Matthew S. Emigh","submitted_at":"2018-02-05T17:24:13Z","abstract_excerpt":"Reinforcement learning in environments with many action-state pairs is challenging. At issue is the number of episodes needed to thoroughly search the policy space. Most conventional heuristics address this search problem in a stochastic manner. This can leave large portions of the policy space unvisited during the early training stages. In this paper, we propose an uncertainty-based, information-theoretic approach for performing guided stochastic searches that more effectively cover the policy space. Our approach is based on the value of information, a criterion that provides the optimal trad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.01518","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1802.01518","created_at":"2026-05-18T00:22:02.285699+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.01518v1","created_at":"2026-05-18T00:22:02.285699+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.01518","created_at":"2026-05-18T00:22:02.285699+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CFUBTL4VDNH","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CFUBTL4VDNHDSON","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CFUBTL4","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH","json":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH.json","graph_json":"https://pith.science/api/pith-number/2CFUBTL4VDNHDSONVBMAOUITUH/graph.json","events_json":"https://pith.science/api/pith-number/2CFUBTL4VDNHDSONVBMAOUITUH/events.json","paper":"https://pith.science/paper/2CFUBTL4"},"agent_actions":{"view_html":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH","download_json":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH.json","view_paper":"https://pith.science/paper/2CFUBTL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.01518&json=true","fetch_graph":"https://pith.science/api/pith-number/2CFUBTL4VDNHDSONVBMAOUITUH/graph.json","fetch_events":"https://pith.science/api/pith-number/2CFUBTL4VDNHDSONVBMAOUITUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH/action/storage_attestation","attest_author":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH/action/author_attestation","sign_citation":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH/action/citation_signature","submit_replication":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH/action/replication_record"}},"created_at":"2026-05-18T00:22:02.285699+00:00","updated_at":"2026-05-18T00:22:02.285699+00:00"}