{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SNLEYIHSEV5PNNXONRIRMMGURU","short_pith_number":"pith:SNLEYIHS","schema_version":"1.0","canonical_sha256":"93564c20f2257af6b6ee6c511630d48d2eff2182fd34253312c2e6cc2a6369ee","source":{"kind":"arxiv","id":"2303.08271","version":1},"attestation_state":"computed","paper":{"title":"Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Merlijn Krale, Nils Jansen, Thiago D. Sim\\~ao","submitted_at":"2023-03-14T23:22:32Z","abstract_excerpt":"We study Markov decision processes (MDPs), where agents have direct control over when and how they gather information, as formalized by action-contingent noiselessly observable MDPs (ACNO-MPDs). In these models, actions consist of two components: a control action that affects the environment, and a measurement action that affects what the agent can observe. To solve ACNO-MDPs, we introduce the act-then-measure (ATM) heuristic, which assumes that we can ignore future state uncertainty when choosing control actions. We show how following this heuristic may lead to shorter policy computation time"},"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":"2303.08271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-14T23:22:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8289aab8c9dc3de6e7562cdc741a6727bcadb56139e3926a514f93e72ca21c87","abstract_canon_sha256":"9ac43537c949e480a74f15ed57d51dc107d76be19be81a30d30d0dea91062b44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:30.826808Z","signature_b64":"7w5e63zEaY7D8KNYGDbjbnWemqiIoJpTqBHrukexL/2kYjg4vcvnRJtuERVCmoPizw/djql6jy5tcWWjZ2deCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93564c20f2257af6b6ee6c511630d48d2eff2182fd34253312c2e6cc2a6369ee","last_reissued_at":"2026-07-05T05:51:30.826403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:30.826403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Merlijn Krale, Nils Jansen, Thiago D. Sim\\~ao","submitted_at":"2023-03-14T23:22:32Z","abstract_excerpt":"We study Markov decision processes (MDPs), where agents have direct control over when and how they gather information, as formalized by action-contingent noiselessly observable MDPs (ACNO-MPDs). In these models, actions consist of two components: a control action that affects the environment, and a measurement action that affects what the agent can observe. To solve ACNO-MDPs, we introduce the act-then-measure (ATM) heuristic, which assumes that we can ignore future state uncertainty when choosing control actions. We show how following this heuristic may lead to shorter policy computation time"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08271","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.08271/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2303.08271","created_at":"2026-07-05T05:51:30.826459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08271v1","created_at":"2026-07-05T05:51:30.826459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08271","created_at":"2026-07-05T05:51:30.826459+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNLEYIHSEV5P","created_at":"2026-07-05T05:51:30.826459+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNLEYIHSEV5PNNXO","created_at":"2026-07-05T05:51:30.826459+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNLEYIHS","created_at":"2026-07-05T05:51:30.826459+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12823","citing_title":"To Measure or Not: A Cost-Sensitive, Selective Measuring Environment for Agricultural Management Decisions with Reinforcement Learning","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU","json":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU.json","graph_json":"https://pith.science/api/pith-number/SNLEYIHSEV5PNNXONRIRMMGURU/graph.json","events_json":"https://pith.science/api/pith-number/SNLEYIHSEV5PNNXONRIRMMGURU/events.json","paper":"https://pith.science/paper/SNLEYIHS"},"agent_actions":{"view_html":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU","download_json":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU.json","view_paper":"https://pith.science/paper/SNLEYIHS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08271&json=true","fetch_graph":"https://pith.science/api/pith-number/SNLEYIHSEV5PNNXONRIRMMGURU/graph.json","fetch_events":"https://pith.science/api/pith-number/SNLEYIHSEV5PNNXONRIRMMGURU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU/action/storage_attestation","attest_author":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU/action/author_attestation","sign_citation":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU/action/citation_signature","submit_replication":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU/action/replication_record"}},"created_at":"2026-07-05T05:51:30.826459+00:00","updated_at":"2026-07-05T05:51:30.826459+00:00"}