{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OFGEU7XIBYMWSRX5GWEGCZGENH","short_pith_number":"pith:OFGEU7XI","canonical_record":{"source":{"id":"2408.10381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-08-19T19:51:53Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4c6ffbb4979785e7db2741e801334e0a3faf5d0b62e69edb79d6caf9953ccb75","abstract_canon_sha256":"78dc86b7ad7df83b1722bbd2dec670f0a6f6fc446f9131fa853941cd55cbb425"},"schema_version":"1.0"},"canonical_sha256":"714c4a7ee80e196946fd35886164c469fbaa23d7847e36f9163d8e3a1eb77e5d","source":{"kind":"arxiv","id":"2408.10381","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10381","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10381v1","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10381","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"pith_short_12","alias_value":"OFGEU7XIBYMW","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"pith_short_16","alias_value":"OFGEU7XIBYMWSRX5","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"pith_short_8","alias_value":"OFGEU7XI","created_at":"2026-07-05T08:57:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OFGEU7XIBYMWSRX5GWEGCZGENH","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-08-19T19:51:53Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4c6ffbb4979785e7db2741e801334e0a3faf5d0b62e69edb79d6caf9953ccb75","abstract_canon_sha256":"78dc86b7ad7df83b1722bbd2dec670f0a6f6fc446f9131fa853941cd55cbb425"},"schema_version":"1.0"},"canonical_sha256":"714c4a7ee80e196946fd35886164c469fbaa23d7847e36f9163d8e3a1eb77e5d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:11.078639Z","signature_b64":"7t7slbQerhkYYxFtgE6XWfuQ5DiWqoutd7JFx94FoiYgo6WQiwQun3NCHcGmpfx0Cngofyofin3gXIq4qu/ZAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"714c4a7ee80e196946fd35886164c469fbaa23d7847e36f9163d8e3a1eb77e5d","last_reissued_at":"2026-07-05T08:57:11.078255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:11.078255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10381","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":"2026-07-05T08:57:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n+HDkcgONumxdXsr14IrgB4lFMcBEKjz/ktUPJ+GZPCLrN2F+OTB4T1ukQeLMYl+xzS8EP6CSXvZ1jFkGdcgCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:52:52.544907Z"},"content_sha256":"385adb370f0f43be0b6b389d140a106c22caab30ac2f433a3ca6008a1a53e05d","schema_version":"1.0","event_id":"sha256:385adb370f0f43be0b6b389d140a106c22caab30ac2f433a3ca6008a1a53e05d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OFGEU7XIBYMWSRX5GWEGCZGENH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Reinforcement Learning in Probabilistic Reward Machines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Xiaofeng Lin, Xuezhou Zhang","submitted_at":"2024-08-19T19:51:53Z","abstract_excerpt":"In this paper, we study reinforcement learning in Markov Decision Processes with Probabilistic Reward Machines (PRMs), a form of non-Markovian reward commonly found in robotics tasks. We design an algorithm for PRMs that achieves a regret bound of $\\widetilde{O}(\\sqrt{HOAT} + H^2O^2A^{3/2} + H\\sqrt{T})$, where $H$ is the time horizon, $O$ is the number of observations, $A$ is the number of actions, and $T$ is the number of time-steps. This result improves over the best-known bound, $\\widetilde{O}(H\\sqrt{OAT})$ of \\citet{pmlr-v206-bourel23a} for MDPs with Deterministic Reward Machines (DRMs), a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10381","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/2408.10381/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":"2026-07-05T08:57:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VhLTgsK/4MXkdjLHvWTeHTzRlzBsdeUEl2Zo/ar8sUKViG0K5HygVk4Ev5FlptUqh4fLVAOKictVZEMzVT35DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:52:52.545881Z"},"content_sha256":"9238ef62cda260c8a020c4cb2d3254c73dea157e8f2c04f76acf01ac74c62a8a","schema_version":"1.0","event_id":"sha256:9238ef62cda260c8a020c4cb2d3254c73dea157e8f2c04f76acf01ac74c62a8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OFGEU7XIBYMWSRX5GWEGCZGENH/bundle.json","state_url":"https://pith.science/pith/OFGEU7XIBYMWSRX5GWEGCZGENH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OFGEU7XIBYMWSRX5GWEGCZGENH/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":"2026-08-21T11:52:52Z","links":{"resolver":"https://pith.science/pith/OFGEU7XIBYMWSRX5GWEGCZGENH","bundle":"https://pith.science/pith/OFGEU7XIBYMWSRX5GWEGCZGENH/bundle.json","state":"https://pith.science/pith/OFGEU7XIBYMWSRX5GWEGCZGENH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OFGEU7XIBYMWSRX5GWEGCZGENH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OFGEU7XIBYMWSRX5GWEGCZGENH","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":"78dc86b7ad7df83b1722bbd2dec670f0a6f6fc446f9131fa853941cd55cbb425","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-08-19T19:51:53Z","title_canon_sha256":"4c6ffbb4979785e7db2741e801334e0a3faf5d0b62e69edb79d6caf9953ccb75"},"schema_version":"1.0","source":{"id":"2408.10381","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10381","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10381v1","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10381","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"pith_short_12","alias_value":"OFGEU7XIBYMW","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"pith_short_16","alias_value":"OFGEU7XIBYMWSRX5","created_at":"2026-07-05T08:57:11Z"},{"alias_kind":"pith_short_8","alias_value":"OFGEU7XI","created_at":"2026-07-05T08:57:11Z"}],"graph_snapshots":[{"event_id":"sha256:9238ef62cda260c8a020c4cb2d3254c73dea157e8f2c04f76acf01ac74c62a8a","target":"graph","created_at":"2026-07-05T08:57:11Z","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/2408.10381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study reinforcement learning in Markov Decision Processes with Probabilistic Reward Machines (PRMs), a form of non-Markovian reward commonly found in robotics tasks. We design an algorithm for PRMs that achieves a regret bound of $\\widetilde{O}(\\sqrt{HOAT} + H^2O^2A^{3/2} + H\\sqrt{T})$, where $H$ is the time horizon, $O$ is the number of observations, $A$ is the number of actions, and $T$ is the number of time-steps. This result improves over the best-known bound, $\\widetilde{O}(H\\sqrt{OAT})$ of \\citet{pmlr-v206-bourel23a} for MDPs with Deterministic Reward Machines (DRMs), a","authors_text":"Xiaofeng Lin, Xuezhou Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-08-19T19:51:53Z","title":"Efficient Reinforcement Learning in Probabilistic Reward Machines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10381","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":"sha256:385adb370f0f43be0b6b389d140a106c22caab30ac2f433a3ca6008a1a53e05d","target":"record","created_at":"2026-07-05T08:57:11Z","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":"78dc86b7ad7df83b1722bbd2dec670f0a6f6fc446f9131fa853941cd55cbb425","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-08-19T19:51:53Z","title_canon_sha256":"4c6ffbb4979785e7db2741e801334e0a3faf5d0b62e69edb79d6caf9953ccb75"},"schema_version":"1.0","source":{"id":"2408.10381","kind":"arxiv","version":1}},"canonical_sha256":"714c4a7ee80e196946fd35886164c469fbaa23d7847e36f9163d8e3a1eb77e5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"714c4a7ee80e196946fd35886164c469fbaa23d7847e36f9163d8e3a1eb77e5d","first_computed_at":"2026-07-05T08:57:11.078255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:11.078255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7t7slbQerhkYYxFtgE6XWfuQ5DiWqoutd7JFx94FoiYgo6WQiwQun3NCHcGmpfx0Cngofyofin3gXIq4qu/ZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:11.078639Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10381","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:385adb370f0f43be0b6b389d140a106c22caab30ac2f433a3ca6008a1a53e05d","sha256:9238ef62cda260c8a020c4cb2d3254c73dea157e8f2c04f76acf01ac74c62a8a"],"state_sha256":"026aa175ea7b15dc8fa17dfceac26116e21af36bc02ff95367b13ddedbce1051"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JpGllvs0TN5iuxn+ZmMh7ypYi6/8KLqE+I153j5mKfn+/T8o0uhdLdnyBZrWsB4DQ6Du/yoRrdnWqv9g9ilmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T11:52:52.551676Z","bundle_sha256":"139edf38ba4e0a4c3d4c517ab865232c70c45ab65fd548c9288f11ec0c6acde0"}}