{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SDDXVNPUJJCOVR4567QZHNZIC2","short_pith_number":"pith:SDDXVNPU","schema_version":"1.0","canonical_sha256":"90c77ab5f44a44eac79df7e193b72816bebcb53ef3967e9950a25228598118c1","source":{"kind":"arxiv","id":"2101.08740","version":1},"attestation_state":"computed","paper":{"title":"Model-based Policy Search for Partially Measurable Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Alberto Dalla Libera, Daniel Nikovski, Diego Romeres, Fabio Amadio, Ruggero Carli","submitted_at":"2021-01-21T17:39:22Z","abstract_excerpt":"In this paper, we propose a Model-Based Reinforcement Learning (MBRL) algorithm for Partially Measurable Systems (PMS), i.e., systems where the state can not be directly measured, but must be estimated through proper state observers. The proposed algorithm, named Monte Carlo Probabilistic Inference for Learning COntrol for Partially Measurable Systems (MC-PILCO4PMS), relies on Gaussian Processes (GPs) to model the system dynamics, and on a Monte Carlo approach to update the policy parameters. W.r.t. previous GP-based MBRL algorithms, MC-PILCO4PMS models explicitly the presence of state observe"},"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":"2101.08740","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-01-21T17:39:22Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"6817bd834b62c5b5ed63199fab65e2a60b4fb911ce5e7f3bd49516568d3ef78c","abstract_canon_sha256":"68ec268761afcf98823f88a81671f3a014e5ed724aeaac29f5afda00fddaeee8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:38.181884Z","signature_b64":"bkYfgsVihmdXHADmrCtCWSDf5ds6fBo16SkoBXnc5z9k3YujAF/kZfZ+EBWZLkPrdSvhKgPKBaDzObxO+18zAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90c77ab5f44a44eac79df7e193b72816bebcb53ef3967e9950a25228598118c1","last_reissued_at":"2026-07-05T02:08:38.181517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:38.181517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-based Policy Search for Partially Measurable Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Alberto Dalla Libera, Daniel Nikovski, Diego Romeres, Fabio Amadio, Ruggero Carli","submitted_at":"2021-01-21T17:39:22Z","abstract_excerpt":"In this paper, we propose a Model-Based Reinforcement Learning (MBRL) algorithm for Partially Measurable Systems (PMS), i.e., systems where the state can not be directly measured, but must be estimated through proper state observers. The proposed algorithm, named Monte Carlo Probabilistic Inference for Learning COntrol for Partially Measurable Systems (MC-PILCO4PMS), relies on Gaussian Processes (GPs) to model the system dynamics, and on a Monte Carlo approach to update the policy parameters. W.r.t. previous GP-based MBRL algorithms, MC-PILCO4PMS models explicitly the presence of state observe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08740","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/2101.08740/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":"2101.08740","created_at":"2026-07-05T02:08:38.181579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.08740v1","created_at":"2026-07-05T02:08:38.181579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08740","created_at":"2026-07-05T02:08:38.181579+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDDXVNPUJJCO","created_at":"2026-07-05T02:08:38.181579+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDDXVNPUJJCOVR45","created_at":"2026-07-05T02:08:38.181579+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDDXVNPU","created_at":"2026-07-05T02:08:38.181579+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/SDDXVNPUJJCOVR4567QZHNZIC2","json":"https://pith.science/pith/SDDXVNPUJJCOVR4567QZHNZIC2.json","graph_json":"https://pith.science/api/pith-number/SDDXVNPUJJCOVR4567QZHNZIC2/graph.json","events_json":"https://pith.science/api/pith-number/SDDXVNPUJJCOVR4567QZHNZIC2/events.json","paper":"https://pith.science/paper/SDDXVNPU"},"agent_actions":{"view_html":"https://pith.science/pith/SDDXVNPUJJCOVR4567QZHNZIC2","download_json":"https://pith.science/pith/SDDXVNPUJJCOVR4567QZHNZIC2.json","view_paper":"https://pith.science/paper/SDDXVNPU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.08740&json=true","fetch_graph":"https://pith.science/api/pith-number/SDDXVNPUJJCOVR4567QZHNZIC2/graph.json","fetch_events":"https://pith.science/api/pith-number/SDDXVNPUJJCOVR4567QZHNZIC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDDXVNPUJJCOVR4567QZHNZIC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDDXVNPUJJCOVR4567QZHNZIC2/action/storage_attestation","attest_author":"https://pith.science/pith/SDDXVNPUJJCOVR4567QZHNZIC2/action/author_attestation","sign_citation":"https://pith.science/pith/SDDXVNPUJJCOVR4567QZHNZIC2/action/citation_signature","submit_replication":"https://pith.science/pith/SDDXVNPUJJCOVR4567QZHNZIC2/action/replication_record"}},"created_at":"2026-07-05T02:08:38.181579+00:00","updated_at":"2026-07-05T02:08:38.181579+00:00"}