{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5MS76HKUU4AGL3KPT5ARLUOU5F","short_pith_number":"pith:5MS76HKU","schema_version":"1.0","canonical_sha256":"eb25ff1d54a70065ed4f9f4115d1d4e94f1febea990167275bef491eb7a39c47","source":{"kind":"arxiv","id":"1902.05795","version":1},"attestation_state":"computed","paper":{"title":"Robust Reinforcement Learning in POMDPs with Incomplete and Noisy Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao He, Xiaoyang Tan, Yuhui Wang","submitted_at":"2019-02-15T12:47:50Z","abstract_excerpt":"In real-world scenarios, the observation data for reinforcement learning with continuous control is commonly noisy and part of it may be dynamically missing over time, which violates the assumption of many current methods developed for this. We addressed the issue within the framework of partially observable Markov Decision Process (POMDP) using a model-based method, in which the transition model is estimated from the incomplete and noisy observations using a newly proposed surrogate loss function with local approximation, while the policy and value function is learned with the help of belief "},"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":"1902.05795","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-15T12:47:50Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a6367fcc1f9f4bc52a42bfde52206016fb177bdc3d800b069beb4683763deaf9","abstract_canon_sha256":"c3da3bb59bd95a974714b457d8a84e1a997870250dcb64709b5c86c9ce7657cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:56.092443Z","signature_b64":"PlBZsvp/0xj8B5HzSBDK9I2Ozc8iqdrk3kDLVDToHEcDqXxYko9DtKt2eDUKpmFU+ixt9V24+sMYC/B+iH3MBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb25ff1d54a70065ed4f9f4115d1d4e94f1febea990167275bef491eb7a39c47","last_reissued_at":"2026-05-17T23:53:56.091746Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:56.091746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Reinforcement Learning in POMDPs with Incomplete and Noisy Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao He, Xiaoyang Tan, Yuhui Wang","submitted_at":"2019-02-15T12:47:50Z","abstract_excerpt":"In real-world scenarios, the observation data for reinforcement learning with continuous control is commonly noisy and part of it may be dynamically missing over time, which violates the assumption of many current methods developed for this. We addressed the issue within the framework of partially observable Markov Decision Process (POMDP) using a model-based method, in which the transition model is estimated from the incomplete and noisy observations using a newly proposed surrogate loss function with local approximation, while the policy and value function is learned with the help of belief "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05795","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1902.05795","created_at":"2026-05-17T23:53:56.091840+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.05795v1","created_at":"2026-05-17T23:53:56.091840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05795","created_at":"2026-05-17T23:53:56.091840+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MS76HKUU4AG","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MS76HKUU4AGL3KP","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MS76HKU","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12262","citing_title":"Missingness-MDPs: Bridging the Theory of Missing Data and POMDPs","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F","json":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F.json","graph_json":"https://pith.science/api/pith-number/5MS76HKUU4AGL3KPT5ARLUOU5F/graph.json","events_json":"https://pith.science/api/pith-number/5MS76HKUU4AGL3KPT5ARLUOU5F/events.json","paper":"https://pith.science/paper/5MS76HKU"},"agent_actions":{"view_html":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F","download_json":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F.json","view_paper":"https://pith.science/paper/5MS76HKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.05795&json=true","fetch_graph":"https://pith.science/api/pith-number/5MS76HKUU4AGL3KPT5ARLUOU5F/graph.json","fetch_events":"https://pith.science/api/pith-number/5MS76HKUU4AGL3KPT5ARLUOU5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F/action/storage_attestation","attest_author":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F/action/author_attestation","sign_citation":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F/action/citation_signature","submit_replication":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F/action/replication_record"}},"created_at":"2026-05-17T23:53:56.091840+00:00","updated_at":"2026-05-17T23:53:56.091840+00:00"}