{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XWJATIVTN3T63JITKAZR5K5W7P","short_pith_number":"pith:XWJATIVT","canonical_record":{"source":{"id":"2306.01243","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T02:46:39Z","cross_cats_sorted":[],"title_canon_sha256":"23979c290603a3b49b044497b2e3859383cd038c8e5e49d631be1ec691217454","abstract_canon_sha256":"3ccbfc78fdd617a179f60a02018fb87bcc5bdd8526bbc2f2bd353d760e745a02"},"schema_version":"1.0"},"canonical_sha256":"bd9209a2b36ee7eda51350331eabb6fbf1c8e03fa5314a3748b80c4875793d15","source":{"kind":"arxiv","id":"2306.01243","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01243","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01243v2","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01243","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"XWJATIVTN3T6","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"XWJATIVTN3T63JIT","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"XWJATIVT","created_at":"2026-07-05T07:05:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XWJATIVTN3T63JITKAZR5K5W7P","target":"record","payload":{"canonical_record":{"source":{"id":"2306.01243","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T02:46:39Z","cross_cats_sorted":[],"title_canon_sha256":"23979c290603a3b49b044497b2e3859383cd038c8e5e49d631be1ec691217454","abstract_canon_sha256":"3ccbfc78fdd617a179f60a02018fb87bcc5bdd8526bbc2f2bd353d760e745a02"},"schema_version":"1.0"},"canonical_sha256":"bd9209a2b36ee7eda51350331eabb6fbf1c8e03fa5314a3748b80c4875793d15","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:43.937888Z","signature_b64":"p0mHGW3/sTOaph8cNfeY6wP+je4PD+LSTQ2os2NLHScLgw6rdW3g6N+fAJYukuXVLKr518xFkTwEBb1dNSjbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd9209a2b36ee7eda51350331eabb6fbf1c8e03fa5314a3748b80c4875793d15","last_reissued_at":"2026-07-05T07:05:43.937386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:43.937386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.01243","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"se7SzBxNp6DPxJkO6A+usssXOkUYQAHg+vhk0dSpJzjc5a+2LEyPmylUTIjD4eKpZNLRPzFwBT22qgzyGUc2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:13:33.621476Z"},"content_sha256":"1f1704a730fd6cc19d010cc0d1ac3aa5646beeeef0416acb377f3cc1f8463f86","schema_version":"1.0","event_id":"sha256:1f1704a730fd6cc19d010cc0d1ac3aa5646beeeef0416acb377f3cc1f8463f86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XWJATIVTN3T63JITKAZR5K5W7P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"H. Vincent Poor, Jie Meng, Mengdi Wang, Minshuo Chen, Yinyu Ye, Yu Bai","submitted_at":"2023-06-02T02:46:39Z","abstract_excerpt":"In real-world reinforcement learning (RL) systems, various forms of {\\it impaired observability} can complicate matters. These situations arise when an agent is unable to observe the most recent state of the system due to latency or lossy channels, yet the agent must still make real-time decisions. This paper introduces a theoretical investigation into efficient RL in control systems where agents must act with delayed and missing state observations. We present algorithms and establish near-optimal regret upper and lower bounds, of the form $\\tilde{\\mathcal{O}}(\\sqrt{{\\rm poly}(H) SAK})$, for R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01243","kind":"arxiv","version":2},"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/2306.01243/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w2XlOgogRygOYe8wBpm+W1Nozf8ICo2JTC13sngnCK6CKXamiOF2DOXExBwWNhLATHKO2GaPBtyihQ7izYEAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:13:33.622477Z"},"content_sha256":"c2da677de54582a42aa693085882bef07fb0a23173c007e62c19d27a9b814e2e","schema_version":"1.0","event_id":"sha256:c2da677de54582a42aa693085882bef07fb0a23173c007e62c19d27a9b814e2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XWJATIVTN3T63JITKAZR5K5W7P/bundle.json","state_url":"https://pith.science/pith/XWJATIVTN3T63JITKAZR5K5W7P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XWJATIVTN3T63JITKAZR5K5W7P/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":"2026-08-10T03:13:33Z","links":{"resolver":"https://pith.science/pith/XWJATIVTN3T63JITKAZR5K5W7P","bundle":"https://pith.science/pith/XWJATIVTN3T63JITKAZR5K5W7P/bundle.json","state":"https://pith.science/pith/XWJATIVTN3T63JITKAZR5K5W7P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XWJATIVTN3T63JITKAZR5K5W7P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XWJATIVTN3T63JITKAZR5K5W7P","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":"3ccbfc78fdd617a179f60a02018fb87bcc5bdd8526bbc2f2bd353d760e745a02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T02:46:39Z","title_canon_sha256":"23979c290603a3b49b044497b2e3859383cd038c8e5e49d631be1ec691217454"},"schema_version":"1.0","source":{"id":"2306.01243","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01243","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01243v2","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01243","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"XWJATIVTN3T6","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"XWJATIVTN3T63JIT","created_at":"2026-07-05T07:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"XWJATIVT","created_at":"2026-07-05T07:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:c2da677de54582a42aa693085882bef07fb0a23173c007e62c19d27a9b814e2e","target":"graph","created_at":"2026-07-05T07:05:43Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.01243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In real-world reinforcement learning (RL) systems, various forms of {\\it impaired observability} can complicate matters. These situations arise when an agent is unable to observe the most recent state of the system due to latency or lossy channels, yet the agent must still make real-time decisions. This paper introduces a theoretical investigation into efficient RL in control systems where agents must act with delayed and missing state observations. We present algorithms and establish near-optimal regret upper and lower bounds, of the form $\\tilde{\\mathcal{O}}(\\sqrt{{\\rm poly}(H) SAK})$, for R","authors_text":"H. Vincent Poor, Jie Meng, Mengdi Wang, Minshuo Chen, Yinyu Ye, Yu Bai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T02:46:39Z","title":"Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01243","kind":"arxiv","version":2},"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":"sha256:1f1704a730fd6cc19d010cc0d1ac3aa5646beeeef0416acb377f3cc1f8463f86","target":"record","created_at":"2026-07-05T07:05:43Z","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":"3ccbfc78fdd617a179f60a02018fb87bcc5bdd8526bbc2f2bd353d760e745a02","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-02T02:46:39Z","title_canon_sha256":"23979c290603a3b49b044497b2e3859383cd038c8e5e49d631be1ec691217454"},"schema_version":"1.0","source":{"id":"2306.01243","kind":"arxiv","version":2}},"canonical_sha256":"bd9209a2b36ee7eda51350331eabb6fbf1c8e03fa5314a3748b80c4875793d15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd9209a2b36ee7eda51350331eabb6fbf1c8e03fa5314a3748b80c4875793d15","first_computed_at":"2026-07-05T07:05:43.937386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:43.937386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p0mHGW3/sTOaph8cNfeY6wP+je4PD+LSTQ2os2NLHScLgw6rdW3g6N+fAJYukuXVLKr518xFkTwEBb1dNSjbAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:43.937888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.01243","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f1704a730fd6cc19d010cc0d1ac3aa5646beeeef0416acb377f3cc1f8463f86","sha256:c2da677de54582a42aa693085882bef07fb0a23173c007e62c19d27a9b814e2e"],"state_sha256":"270d5f1cb1acc2b6c6c698268e204bfbec6eb8547ea1d1f445c4a815c8b13d29"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QWPx62ViqEyyOagCBZ5tm2+axQrekZbxdUmfFhlIkhtzA6LKjkCgYLByPg8+1EuV3staytSFnVhgu42Ui6Y7BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:13:33.628199Z","bundle_sha256":"8a2895e65222ef78e14022d76223f4a0f49352f901c800f74583499474e9e4a2"}}