{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2CFUBTL4VDNHDSONVBMAOUITUH","short_pith_number":"pith:2CFUBTL4","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"},"canonical_sha256":"d08b40cd7ca8da71c9cda858075113a1fa5863cf18d14d93805974be3d25bb88","source":{"kind":"arxiv","id":"1802.01518","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.01518","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"1802.01518v1","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.01518","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"2CFUBTL4VDNH","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2CFUBTL4VDNHDSON","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2CFUBTL4","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2CFUBTL4VDNHDSONVBMAOUITUH","target":"record","payload":{"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"},"canonical_sha256":"d08b40cd7ca8da71c9cda858075113a1fa5863cf18d14d93805974be3d25bb88","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"},"source_kind":"arxiv","source_id":"1802.01518","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7tiYqlBlaJ+5I4yrzQpUvqg+Jj56KlrJc21PMma0dJS3x8EpGcBElkM8DQcG2yRR9YatyfrbOA2if49KW6zwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:48:38.397861Z"},"content_sha256":"cf9aeccb51061648556a0f1beb289191656607b50cf00ddf131b61b7bfea70ec","schema_version":"1.0","event_id":"sha256:cf9aeccb51061648556a0f1beb289191656607b50cf00ddf131b61b7bfea70ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2CFUBTL4VDNHDSONVBMAOUITUH","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pim5Omnq/JuOj2Hv4fMsHA+Okh1v7Cpzckn04mLbjCBQO9dziVmD3DkLKXtCCIQPtxqew00El2CwXl3HoveHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T08:48:38.398201Z"},"content_sha256":"6b3dd0a80c2ec691ef1b287026c5a8be0d84eef6778bf995ac2fbac0ea7e183e","schema_version":"1.0","event_id":"sha256:6b3dd0a80c2ec691ef1b287026c5a8be0d84eef6778bf995ac2fbac0ea7e183e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH/bundle.json","state_url":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2CFUBTL4VDNHDSONVBMAOUITUH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T08:48:38Z","links":{"resolver":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH","bundle":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH/bundle.json","state":"https://pith.science/pith/2CFUBTL4VDNHDSONVBMAOUITUH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2CFUBTL4VDNHDSONVBMAOUITUH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2CFUBTL4VDNHDSONVBMAOUITUH","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":"4929d02d4edd60e7a511c5959bad9b8040727adad1486985c3c1b77a986f793b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-05T17:24:13Z","title_canon_sha256":"4a2b7fa4f3869d5660a395a8e2408d8b5f1c0c920b713349e2593eab108914a0"},"schema_version":"1.0","source":{"id":"1802.01518","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.01518","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"1802.01518v1","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.01518","created_at":"2026-05-18T00:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"2CFUBTL4VDNH","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2CFUBTL4VDNHDSON","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2CFUBTL4","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:6b3dd0a80c2ec691ef1b287026c5a8be0d84eef6778bf995ac2fbac0ea7e183e","target":"graph","created_at":"2026-05-18T00:22:02Z","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"},"paper":{"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","authors_text":"Isaac J. Sledge, Jose C. Principe, Matthew S. Emigh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-05T17:24:13Z","title":"Guided Policy Exploration for Markov Decision Processes using an Uncertainty-Based Value-of-Information Criterion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.01518","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:cf9aeccb51061648556a0f1beb289191656607b50cf00ddf131b61b7bfea70ec","target":"record","created_at":"2026-05-18T00:22:02Z","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":"4929d02d4edd60e7a511c5959bad9b8040727adad1486985c3c1b77a986f793b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-05T17:24:13Z","title_canon_sha256":"4a2b7fa4f3869d5660a395a8e2408d8b5f1c0c920b713349e2593eab108914a0"},"schema_version":"1.0","source":{"id":"1802.01518","kind":"arxiv","version":1}},"canonical_sha256":"d08b40cd7ca8da71c9cda858075113a1fa5863cf18d14d93805974be3d25bb88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d08b40cd7ca8da71c9cda858075113a1fa5863cf18d14d93805974be3d25bb88","first_computed_at":"2026-05-18T00:22:02.285616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:02.285616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aodoz9dGYmGZyn64edG6Zp0X4TxhBnIslpD9Lum+cKkQy1J6UYBP1jii4wJ6oKZF+vxilgZgpVygg/8TspecDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:02.286219Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.01518","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf9aeccb51061648556a0f1beb289191656607b50cf00ddf131b61b7bfea70ec","sha256:6b3dd0a80c2ec691ef1b287026c5a8be0d84eef6778bf995ac2fbac0ea7e183e"],"state_sha256":"4db5d733aa0931edf59d1adb88ea8b39e3706d327a16d2a982a250bba9028467"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ToJ9lsAknyQRrrJc2TzG1DuFRR7KBG9MseegHrhtEHaWqM/WWdukPGuDrMZeEvo+OB21FSK1WQd8TI4XGR/FBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T08:48:38.400155Z","bundle_sha256":"bacdc110de6ed60f246e740ba62a90ef8e806cea918a81834a330b694b6b4b38"}}