{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5MS76HKUU4AGL3KPT5ARLUOU5F","short_pith_number":"pith:5MS76HKU","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"},"canonical_sha256":"eb25ff1d54a70065ed4f9f4115d1d4e94f1febea990167275bef491eb7a39c47","source":{"kind":"arxiv","id":"1902.05795","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05795","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05795v1","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05795","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"pith_short_12","alias_value":"5MS76HKUU4AG","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5MS76HKUU4AGL3KP","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5MS76HKU","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5MS76HKUU4AGL3KPT5ARLUOU5F","target":"record","payload":{"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"},"canonical_sha256":"eb25ff1d54a70065ed4f9f4115d1d4e94f1febea990167275bef491eb7a39c47","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"},"source_kind":"arxiv","source_id":"1902.05795","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I7QT6uMjfRFWsSbegFsUGxRdjjL6ypyWpKCZf9lQ4LWMdlU1N3wYwZS9zoHhkCVUMs/OLc2Gztzd9q6bC3qDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:53:45.376043Z"},"content_sha256":"3b050d6520e1e35bf083c37e6557a4171b37746a5986e52351c96af5f680f040","schema_version":"1.0","event_id":"sha256:3b050d6520e1e35bf083c37e6557a4171b37746a5986e52351c96af5f680f040"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5MS76HKUU4AGL3KPT5ARLUOU5F","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:53:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xfvvipfjbRVP36O66kM+vHPGix8aQZvzcI1pevNEBMPYQeNwKtLpHCuSWkg+JJL3RJTEd33cjxPML91AlfvnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:53:45.376730Z"},"content_sha256":"2d98587263bd7cef11a59caa76329f0120c91eba6b6c1a1dc47b09543e04e3f0","schema_version":"1.0","event_id":"sha256:2d98587263bd7cef11a59caa76329f0120c91eba6b6c1a1dc47b09543e04e3f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F/bundle.json","state_url":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5MS76HKUU4AGL3KPT5ARLUOU5F/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":"2026-05-31T12:53:45Z","links":{"resolver":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F","bundle":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F/bundle.json","state":"https://pith.science/pith/5MS76HKUU4AGL3KPT5ARLUOU5F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5MS76HKUU4AGL3KPT5ARLUOU5F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5MS76HKUU4AGL3KPT5ARLUOU5F","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":"c3da3bb59bd95a974714b457d8a84e1a997870250dcb64709b5c86c9ce7657cd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-15T12:47:50Z","title_canon_sha256":"a6367fcc1f9f4bc52a42bfde52206016fb177bdc3d800b069beb4683763deaf9"},"schema_version":"1.0","source":{"id":"1902.05795","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.05795","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"arxiv_version","alias_value":"1902.05795v1","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.05795","created_at":"2026-05-17T23:53:56Z"},{"alias_kind":"pith_short_12","alias_value":"5MS76HKUU4AG","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5MS76HKUU4AGL3KP","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5MS76HKU","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:2d98587263bd7cef11a59caa76329f0120c91eba6b6c1a1dc47b09543e04e3f0","target":"graph","created_at":"2026-05-17T23:53:56Z","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":"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 ","authors_text":"Hao He, Xiaoyang Tan, Yuhui Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-15T12:47:50Z","title":"Robust Reinforcement Learning in POMDPs with Incomplete and Noisy Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.05795","kind":"arxiv","version":1},"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":"sha256:3b050d6520e1e35bf083c37e6557a4171b37746a5986e52351c96af5f680f040","target":"record","created_at":"2026-05-17T23:53:56Z","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":"c3da3bb59bd95a974714b457d8a84e1a997870250dcb64709b5c86c9ce7657cd","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-15T12:47:50Z","title_canon_sha256":"a6367fcc1f9f4bc52a42bfde52206016fb177bdc3d800b069beb4683763deaf9"},"schema_version":"1.0","source":{"id":"1902.05795","kind":"arxiv","version":1}},"canonical_sha256":"eb25ff1d54a70065ed4f9f4115d1d4e94f1febea990167275bef491eb7a39c47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb25ff1d54a70065ed4f9f4115d1d4e94f1febea990167275bef491eb7a39c47","first_computed_at":"2026-05-17T23:53:56.091746Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:56.091746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PlBZsvp/0xj8B5HzSBDK9I2Ozc8iqdrk3kDLVDToHEcDqXxYko9DtKt2eDUKpmFU+ixt9V24+sMYC/B+iH3MBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:56.092443Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.05795","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b050d6520e1e35bf083c37e6557a4171b37746a5986e52351c96af5f680f040","sha256:2d98587263bd7cef11a59caa76329f0120c91eba6b6c1a1dc47b09543e04e3f0"],"state_sha256":"a80bcba50bb4d6e9bc127f3f60242459f6db943b06ddd09e1836066d21c4db67"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6cP0dkVFg8hJKB04h5euNmkOPvxdSs1826Jb1A1Y4d6PcGQEulycZPAmL2Bdqg4getU5qUhqVva+kGXXoicAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T12:53:45.380199Z","bundle_sha256":"1ab6508bb920df239581834bc11ecbd111936f5e74851b815866ebef7bacdcf9"}}