{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:UA3L7RZH6RBMPTVIWSTRW5UMHJ","short_pith_number":"pith:UA3L7RZH","schema_version":"1.0","canonical_sha256":"a036bfc727f442c7cea8b4a71b768c3a69d4184c0287b1b2bd9a983b223f883d","source":{"kind":"arxiv","id":"1702.08628","version":3},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1702.08628","created_at":"2026-05-18T00:23:09.148746+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.08628v3","created_at":"2026-05-18T00:23:09.148746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08628","created_at":"2026-05-18T00:23:09.148746+00:00"},{"alias_kind":"pith_short_12","alias_value":"UA3L7RZH6RBM","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"UA3L7RZH6RBMPTVI","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"UA3L7RZH","created_at":"2026-05-18T12:31:46.661854+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/UA3L7RZH6RBMPTVIWSTRW5UMHJ","json":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ.json","graph_json":"https://pith.science/api/pith-number/UA3L7RZH6RBMPTVIWSTRW5UMHJ/graph.json","events_json":"https://pith.science/api/pith-number/UA3L7RZH6RBMPTVIWSTRW5UMHJ/events.json","paper":"https://pith.science/paper/UA3L7RZH"},"agent_actions":{"view_html":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ","download_json":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ.json","view_paper":"https://pith.science/paper/UA3L7RZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.08628&json=true","fetch_graph":"https://pith.science/api/pith-number/UA3L7RZH6RBMPTVIWSTRW5UMHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/UA3L7RZH6RBMPTVIWSTRW5UMHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ/action/storage_attestation","attest_author":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ/action/author_attestation","sign_citation":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ/action/citation_signature","submit_replication":"https://pith.science/pith/UA3L7RZH6RBMPTVIWSTRW5UMHJ/action/replication_record"}},"created_at":"2026-05-18T00:23:09.148746+00:00","updated_at":"2026-05-18T00:23:09.148746+00:00"}