{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:UA3L7RZH6RBMPTVIWSTRW5UMHJ","short_pith_number":"pith:UA3L7RZH","canonical_record":{"source":{"id":"1702.08628","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-28T03:23:20Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"3e6df532562ba9379d529a6aa03ddac03883492e688e1a2d9f9a984201fef15a","abstract_canon_sha256":"170cf8640ebd8e43b0050f4ceca211d6607b10183fcecb94ee368fa989c1a64c"},"schema_version":"1.0"},"canonical_sha256":"a036bfc727f442c7cea8b4a71b768c3a69d4184c0287b1b2bd9a983b223f883d","source":{"kind":"arxiv","id":"1702.08628","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08628","created_at":"2026-05-18T00:23:09Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08628v3","created_at":"2026-05-18T00:23:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08628","created_at":"2026-05-18T00:23:09Z"},{"alias_kind":"pith_short_12","alias_value":"UA3L7RZH6RBM","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UA3L7RZH6RBMPTVI","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UA3L7RZH","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:UA3L7RZH6RBMPTVIWSTRW5UMHJ","target":"record","payload":{"canonical_record":{"source":{"id":"1702.08628","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-28T03:23:20Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"3e6df532562ba9379d529a6aa03ddac03883492e688e1a2d9f9a984201fef15a","abstract_canon_sha256":"170cf8640ebd8e43b0050f4ceca211d6607b10183fcecb94ee368fa989c1a64c"},"schema_version":"1.0"},"canonical_sha256":"a036bfc727f442c7cea8b4a71b768c3a69d4184c0287b1b2bd9a983b223f883d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:09.149289Z","signature_b64":"kwDx9kTyAAMHQxdjVGHQFx7ERYQCVj6AYVy7JbXQM6jUvlF6iPRb02Tmp6FZpUK8lBgmrqSBklohQtMPDdP6BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a036bfc727f442c7cea8b4a71b768c3a69d4184c0287b1b2bd9a983b223f883d","last_reissued_at":"2026-05-18T00:23:09.148650Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:09.148650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.08628","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:23:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hHnGO7T3KAHANW8e7xAkNLt60xQBl7ynpl7EADwqoa9zxywRaVgLjQOQ2G/H2Ey87NdAoAzcY++0GIQ0QkbVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T14:00:03.787126Z"},"content_sha256":"6f116dc2f222fd8c7ed448a0f80702d6bda121cb4b0b120e02c16c2db891f546","schema_version":"1.0","event_id":"sha256:6f116dc2f222fd8c7ed448a0f80702d6bda121cb4b0b120e02c16c2db891f546"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:UA3L7RZH6RBMPTVIWSTRW5UMHJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Analysis of Agent Expertise in Ms. Pac-Man using Value-of-Information-based Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Isaac J. Sledge, Jose C. Principe","submitted_at":"2017-02-28T03:23:20Z","abstract_excerpt":"Conventional reinforcement learning methods for Markov decision processes rely on weakly-guided, stochastic searches to drive the learning process. It can therefore be difficult to predict what agent behaviors might emerge. In this paper, we consider an information-theoretic cost function for performing constrained stochastic searches that promote the formation of risk-averse to risk-favoring behaviors. This cost function is the value of information, which provides the optimal trade-off between the expected return of a policy and the policy's complexity; policy complexity is measured by number"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08628","kind":"arxiv","version":3},"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":"2026-05-18T00:23:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VkQfdhe6UlTUv7gOYfoNfklWchLfNQLtAefbDzK2MpF8XzDH0fROiesEjvFuAzjgp7pcy76U2pTS0kGKs4kBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T14:00:03.787488Z"},"content_sha256":"716694fe4ee9966f09e825f2df930dc3ee2b2147c00d96be59a98c738d14256a","schema_version":"1.0","event_id":"sha256:716694fe4ee9966f09e825f2df930dc3ee2b2147c00d96be59a98c738d14256a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ/bundle.json","state_url":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ/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":"2026-06-03T14:00:03Z","links":{"resolver":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ","bundle":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ/bundle.json","state":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UA3L7RZH6RBMPTVIWSTRW5UMHJ","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":"170cf8640ebd8e43b0050f4ceca211d6607b10183fcecb94ee368fa989c1a64c","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-28T03:23:20Z","title_canon_sha256":"3e6df532562ba9379d529a6aa03ddac03883492e688e1a2d9f9a984201fef15a"},"schema_version":"1.0","source":{"id":"1702.08628","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08628","created_at":"2026-05-18T00:23:09Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08628v3","created_at":"2026-05-18T00:23:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08628","created_at":"2026-05-18T00:23:09Z"},{"alias_kind":"pith_short_12","alias_value":"UA3L7RZH6RBM","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UA3L7RZH6RBMPTVI","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UA3L7RZH","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:716694fe4ee9966f09e825f2df930dc3ee2b2147c00d96be59a98c738d14256a","target":"graph","created_at":"2026-05-18T00:23:09Z","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":"Conventional reinforcement learning methods for Markov decision processes rely on weakly-guided, stochastic searches to drive the learning process. It can therefore be difficult to predict what agent behaviors might emerge. In this paper, we consider an information-theoretic cost function for performing constrained stochastic searches that promote the formation of risk-averse to risk-favoring behaviors. This cost function is the value of information, which provides the optimal trade-off between the expected return of a policy and the policy's complexity; policy complexity is measured by number","authors_text":"Isaac J. Sledge, Jose C. Principe","cross_cats":["cs.AI","cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-28T03:23:20Z","title":"Analysis of Agent Expertise in Ms. Pac-Man using Value-of-Information-based Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08628","kind":"arxiv","version":3},"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":"sha256:6f116dc2f222fd8c7ed448a0f80702d6bda121cb4b0b120e02c16c2db891f546","target":"record","created_at":"2026-05-18T00:23:09Z","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":"170cf8640ebd8e43b0050f4ceca211d6607b10183fcecb94ee368fa989c1a64c","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-28T03:23:20Z","title_canon_sha256":"3e6df532562ba9379d529a6aa03ddac03883492e688e1a2d9f9a984201fef15a"},"schema_version":"1.0","source":{"id":"1702.08628","kind":"arxiv","version":3}},"canonical_sha256":"a036bfc727f442c7cea8b4a71b768c3a69d4184c0287b1b2bd9a983b223f883d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a036bfc727f442c7cea8b4a71b768c3a69d4184c0287b1b2bd9a983b223f883d","first_computed_at":"2026-05-18T00:23:09.148650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:09.148650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kwDx9kTyAAMHQxdjVGHQFx7ERYQCVj6AYVy7JbXQM6jUvlF6iPRb02Tmp6FZpUK8lBgmrqSBklohQtMPDdP6BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:09.149289Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.08628","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f116dc2f222fd8c7ed448a0f80702d6bda121cb4b0b120e02c16c2db891f546","sha256:716694fe4ee9966f09e825f2df930dc3ee2b2147c00d96be59a98c738d14256a"],"state_sha256":"c78dc1042940f3520d889f9df3ba18a5c25be39255d45ff5a06f1276ece06126"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5YBPmezCjUhrOkiNR/TIOFdocY8G06O2HhK/VSP7Tev07KnI3FJNQdKHo8JsO2RV2ia5777YR/sInJzo1yz+CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T14:00:03.789479Z","bundle_sha256":"25ff15cf06fe949e2cf346960f03997a50851281b5cfa4335ece4bb20e959d5b"}}