{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NVIIW3GS3WDEGXVCHMWZ2FW7XI","short_pith_number":"pith:NVIIW3GS","schema_version":"1.0","canonical_sha256":"6d508b6cd2dd86435ea23b2d9d16dfba00c9f92d7ae283a9385779d3f586575a","source":{"kind":"arxiv","id":"2002.05138","version":3},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2002.05138","created_at":"2026-07-05T02:44:02.093122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.05138v3","created_at":"2026-07-05T02:44:02.093122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.05138","created_at":"2026-07-05T02:44:02.093122+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVIIW3GS3WDE","created_at":"2026-07-05T02:44:02.093122+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVIIW3GS3WDEGXVC","created_at":"2026-07-05T02:44:02.093122+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVIIW3GS","created_at":"2026-07-05T02:44:02.093122+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10804","citing_title":"Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI","json":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI.json","graph_json":"https://pith.science/api/pith-number/NVIIW3GS3WDEGXVCHMWZ2FW7XI/graph.json","events_json":"https://pith.science/api/pith-number/NVIIW3GS3WDEGXVCHMWZ2FW7XI/events.json","paper":"https://pith.science/paper/NVIIW3GS"},"agent_actions":{"view_html":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI","download_json":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI.json","view_paper":"https://pith.science/paper/NVIIW3GS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.05138&json=true","fetch_graph":"https://pith.science/api/pith-number/NVIIW3GS3WDEGXVCHMWZ2FW7XI/graph.json","fetch_events":"https://pith.science/api/pith-number/NVIIW3GS3WDEGXVCHMWZ2FW7XI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI/action/storage_attestation","attest_author":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI/action/author_attestation","sign_citation":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI/action/citation_signature","submit_replication":"https://pith.science/pith/NVIIW3GS3WDEGXVCHMWZ2FW7XI/action/replication_record"}},"created_at":"2026-07-05T02:44:02.093122+00:00","updated_at":"2026-07-05T02:44:02.093122+00:00"}