{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TU5FPFYPTIVI4ON7TNGMNHSBAM","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":"62713fc4699158b531ba356b85c5d34149c4bdc77d5702a9b3f449a54805311d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T15:40:21Z","title_canon_sha256":"6ee6e7b5dde052146ca3f3c2efec34c590b3e2a3f271e29339777f3ade57f3d6"},"schema_version":"1.0","source":{"id":"2006.14389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.14389","created_at":"2026-07-05T01:13:32Z"},{"alias_kind":"arxiv_version","alias_value":"2006.14389v1","created_at":"2026-07-05T01:13:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.14389","created_at":"2026-07-05T01:13:32Z"},{"alias_kind":"pith_short_12","alias_value":"TU5FPFYPTIVI","created_at":"2026-07-05T01:13:32Z"},{"alias_kind":"pith_short_16","alias_value":"TU5FPFYPTIVI4ON7","created_at":"2026-07-05T01:13:32Z"},{"alias_kind":"pith_short_8","alias_value":"TU5FPFYP","created_at":"2026-07-05T01:13:32Z"}],"graph_snapshots":[{"event_id":"sha256:1c420c1151563ce4580e3b0854b08ce1ef6299b5e78e220c94750f99b977ad2a","target":"graph","created_at":"2026-07-05T01:13:32Z","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/2006.14389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider un-discounted reinforcement learning (RL) in Markov decision processes (MDPs) under drifting non-stationarity, i.e., both the reward and state transition distributions are allowed to evolve over time, as long as their respective total variations, quantified by suitable metrics, do not exceed certain variation budgets. We first develop the Sliding Window Upper-Confidence bound for Reinforcement Learning with Confidence Widening (SWUCRL2-CW) algorithm, and establish its dynamic regret bound when the variation budgets are known. In addition, we propose the Bandit-over-Reinforcement Le","authors_text":"David Simchi-Levi, Ruihao Zhu, Wang Chi Cheung","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T15:40:21Z","title":"Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.14389","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:bcbe982e81abd69bb5a3ce7a411eec87e34752d905455bd81d8954dfb223970a","target":"record","created_at":"2026-07-05T01:13:32Z","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":"62713fc4699158b531ba356b85c5d34149c4bdc77d5702a9b3f449a54805311d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-24T15:40:21Z","title_canon_sha256":"6ee6e7b5dde052146ca3f3c2efec34c590b3e2a3f271e29339777f3ade57f3d6"},"schema_version":"1.0","source":{"id":"2006.14389","kind":"arxiv","version":1}},"canonical_sha256":"9d3a57970f9a2a8e39bf9b4cc69e41032eab28273a656d6e07eeea644ab1b5f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d3a57970f9a2a8e39bf9b4cc69e41032eab28273a656d6e07eeea644ab1b5f5","first_computed_at":"2026-07-05T01:13:32.106290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:13:32.106290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CK67ERg4YzhLsFkgvG6hyMz9u/mFRq3rEBJrnxtS7QGtTwWchrM+JQXC/e/vMo8pbPtq/GebbaZd/dt0UeQcBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:13:32.106762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.14389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcbe982e81abd69bb5a3ce7a411eec87e34752d905455bd81d8954dfb223970a","sha256:1c420c1151563ce4580e3b0854b08ce1ef6299b5e78e220c94750f99b977ad2a"],"state_sha256":"c7b70313b7869a43528faab1a896b03e6fb1774b8d1d5455f71b61ca9e76d622"}