{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:NVIIW3GS3WDEGXVCHMWZ2FW7XI","short_pith_number":"pith:NVIIW3GS","canonical_record":{"source":{"id":"2002.05138","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T18:30:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"223c33aad8736d1f0b0164e8fc29e8f0f5e402006a0f3997c5f5360e377cfa2c","abstract_canon_sha256":"8ebdcc6d0cae0086d709d49a3f75a82050bf5c73e74dd35feaae204118d600b7"},"schema_version":"1.0"},"canonical_sha256":"6d508b6cd2dd86435ea23b2d9d16dfba00c9f92d7ae283a9385779d3f586575a","source":{"kind":"arxiv","id":"2002.05138","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05138","created_at":"2026-07-05T02:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05138v3","created_at":"2026-07-05T02:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05138","created_at":"2026-07-05T02:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"NVIIW3GS3WDE","created_at":"2026-07-05T02:44:02Z"},{"alias_kind":"pith_short_16","alias_value":"NVIIW3GS3WDEGXVC","created_at":"2026-07-05T02:44:02Z"},{"alias_kind":"pith_short_8","alias_value":"NVIIW3GS","created_at":"2026-07-05T02:44:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:NVIIW3GS3WDEGXVCHMWZ2FW7XI","target":"record","payload":{"canonical_record":{"source":{"id":"2002.05138","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T18:30:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"223c33aad8736d1f0b0164e8fc29e8f0f5e402006a0f3997c5f5360e377cfa2c","abstract_canon_sha256":"8ebdcc6d0cae0086d709d49a3f75a82050bf5c73e74dd35feaae204118d600b7"},"schema_version":"1.0"},"canonical_sha256":"6d508b6cd2dd86435ea23b2d9d16dfba00c9f92d7ae283a9385779d3f586575a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:02.093526Z","signature_b64":"HJAzE/jEXM5vSnUPNUquFbjW/fvp6uQoy3xgo1mP/64lKrazdyGE/bJGKNGBPcNV2EEkQQ3v6ldB6qlbrM/sDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d508b6cd2dd86435ea23b2d9d16dfba00c9f92d7ae283a9385779d3f586575a","last_reissued_at":"2026-07-05T02:44:02.093066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:02.093066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.05138","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F2H0j87EMYMSSlBBhedh7nYDnneZlAQb9j/GUAoouzw0itQMf+aEElF75KC6einJLvaUpvX25961w/9+6Cr8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:29:31.141073Z"},"content_sha256":"beda36f981dca0fd4a8a608f625ce252acd49b0407d4fff208932ff4ac0232eb","schema_version":"1.0","event_id":"sha256:beda36f981dca0fd4a8a608f625ce252acd49b0407d4fff208932ff4ac0232eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:NVIIW3GS3WDEGXVCHMWZ2FW7XI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regret Bounds for Discounted MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hao Su, Shuang Liu","submitted_at":"2020-02-12T18:30:09Z","abstract_excerpt":"Reinforcement learning (RL) has traditionally been understood from an episodic perspective; the concept of non-episodic RL, where there is no restart and therefore no reliable recovery, remains elusive. A fundamental question in non-episodic RL is how to measure the performance of a learner and derive algorithms to maximize such performance. Conventional wisdom is to maximize the difference between the average reward received by the learner and the maximal long-term average reward. In this paper, we argue that if the total time budget is relatively limited compared to the complexity of the env"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05138","kind":"arxiv","version":3},"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/2002.05138/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":"2026-07-05T02:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fgzo0lJWlPU32fcd0Vo54/qrSGi9GrYtdZ18ITtn3Mk+AmWr6jsYSObLBGOHVpOICgmb/hlVMpkO0O/wodEBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:29:31.141589Z"},"content_sha256":"9f56a681f651ddf75b481cc3417d849ca91ccb2f104f3b7a3c53b505943f80de","schema_version":"1.0","event_id":"sha256:9f56a681f651ddf75b481cc3417d849ca91ccb2f104f3b7a3c53b505943f80de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI/bundle.json","state_url":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI/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":"2026-08-11T03:29:31Z","links":{"resolver":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI","bundle":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI/bundle.json","state":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NVIIW3GS3WDEGXVCHMWZ2FW7XI","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":"8ebdcc6d0cae0086d709d49a3f75a82050bf5c73e74dd35feaae204118d600b7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T18:30:09Z","title_canon_sha256":"223c33aad8736d1f0b0164e8fc29e8f0f5e402006a0f3997c5f5360e377cfa2c"},"schema_version":"1.0","source":{"id":"2002.05138","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.05138","created_at":"2026-07-05T02:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"2002.05138v3","created_at":"2026-07-05T02:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05138","created_at":"2026-07-05T02:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"NVIIW3GS3WDE","created_at":"2026-07-05T02:44:02Z"},{"alias_kind":"pith_short_16","alias_value":"NVIIW3GS3WDEGXVC","created_at":"2026-07-05T02:44:02Z"},{"alias_kind":"pith_short_8","alias_value":"NVIIW3GS","created_at":"2026-07-05T02:44:02Z"}],"graph_snapshots":[{"event_id":"sha256:9f56a681f651ddf75b481cc3417d849ca91ccb2f104f3b7a3c53b505943f80de","target":"graph","created_at":"2026-07-05T02:44:02Z","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/2002.05138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has traditionally been understood from an episodic perspective; the concept of non-episodic RL, where there is no restart and therefore no reliable recovery, remains elusive. A fundamental question in non-episodic RL is how to measure the performance of a learner and derive algorithms to maximize such performance. Conventional wisdom is to maximize the difference between the average reward received by the learner and the maximal long-term average reward. In this paper, we argue that if the total time budget is relatively limited compared to the complexity of the env","authors_text":"Hao Su, Shuang Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T18:30:09Z","title":"Regret Bounds for Discounted MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.05138","kind":"arxiv","version":3},"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:beda36f981dca0fd4a8a608f625ce252acd49b0407d4fff208932ff4ac0232eb","target":"record","created_at":"2026-07-05T02:44:02Z","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":"8ebdcc6d0cae0086d709d49a3f75a82050bf5c73e74dd35feaae204118d600b7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T18:30:09Z","title_canon_sha256":"223c33aad8736d1f0b0164e8fc29e8f0f5e402006a0f3997c5f5360e377cfa2c"},"schema_version":"1.0","source":{"id":"2002.05138","kind":"arxiv","version":3}},"canonical_sha256":"6d508b6cd2dd86435ea23b2d9d16dfba00c9f92d7ae283a9385779d3f586575a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d508b6cd2dd86435ea23b2d9d16dfba00c9f92d7ae283a9385779d3f586575a","first_computed_at":"2026-07-05T02:44:02.093066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:02.093066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HJAzE/jEXM5vSnUPNUquFbjW/fvp6uQoy3xgo1mP/64lKrazdyGE/bJGKNGBPcNV2EEkQQ3v6ldB6qlbrM/sDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:02.093526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.05138","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:beda36f981dca0fd4a8a608f625ce252acd49b0407d4fff208932ff4ac0232eb","sha256:9f56a681f651ddf75b481cc3417d849ca91ccb2f104f3b7a3c53b505943f80de"],"state_sha256":"340fa87f9b35643398b87f2edbae32708a505b3f762f74f3c638a0ea3687b9f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kt7QF1wnDvg94XDxkhPKBamFRHVNJ/Np2x0SMs7AgdcJJdA8gFddeSVKE8N0+N3htyj2+K59mTyX1uRvfAy9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:29:31.148490Z","bundle_sha256":"74742d781c95e768af639d2650b1465d2a5a4f7b04fb4dc8985159b1741b3b4f"}}