{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RM7YDBGQY4NWFCJKK5A2RMD52S","short_pith_number":"pith:RM7YDBGQ","canonical_record":{"source":{"id":"2010.03161","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T04:55:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"02e875b3a3aa36a2cd93927d8b05e2d8109b4b8facc576171b9ffa6f7d934cbd","abstract_canon_sha256":"7d01d3acf330a29f0292cd8d24c454815821b8057ad6b8837c0b9bcd432defa6"},"schema_version":"1.0"},"canonical_sha256":"8b3f8184d0c71b62892a5741a8b07dd4a4b7695df21548360f16f33d98dab366","source":{"kind":"arxiv","id":"2010.03161","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.03161","created_at":"2026-07-05T04:50:00Z"},{"alias_kind":"arxiv_version","alias_value":"2010.03161v4","created_at":"2026-07-05T04:50:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03161","created_at":"2026-07-05T04:50:00Z"},{"alias_kind":"pith_short_12","alias_value":"RM7YDBGQY4NW","created_at":"2026-07-05T04:50:00Z"},{"alias_kind":"pith_short_16","alias_value":"RM7YDBGQY4NWFCJK","created_at":"2026-07-05T04:50:00Z"},{"alias_kind":"pith_short_8","alias_value":"RM7YDBGQ","created_at":"2026-07-05T04:50:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RM7YDBGQY4NWFCJKK5A2RMD52S","target":"record","payload":{"canonical_record":{"source":{"id":"2010.03161","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T04:55:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"02e875b3a3aa36a2cd93927d8b05e2d8109b4b8facc576171b9ffa6f7d934cbd","abstract_canon_sha256":"7d01d3acf330a29f0292cd8d24c454815821b8057ad6b8837c0b9bcd432defa6"},"schema_version":"1.0"},"canonical_sha256":"8b3f8184d0c71b62892a5741a8b07dd4a4b7695df21548360f16f33d98dab366","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:50:00.695798Z","signature_b64":"d0+wudYJBmo/l+9lQKCGxjR2hi2reO3CWlh+03+V1Nrvgy3xxJ+Le0JkvgYF9V8FR485IPSAamJdBoLCkMvNDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b3f8184d0c71b62892a5741a8b07dd4a4b7695df21548360f16f33d98dab366","last_reissued_at":"2026-07-05T04:50:00.695124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:50:00.695124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.03161","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:50:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yoMYr9s6zn9YIDa1K05xhnhGt0McqL1FOtr7YJid7B2HM3C+grXjW7ssQ/fnnQCKEaTL3zKblN5sBB3s2FeWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:28:48.094092Z"},"content_sha256":"783ac0d2d89cb7595120064b56216e633224904c3e1546bf78b88b39a7c44286","schema_version":"1.0","event_id":"sha256:783ac0d2d89cb7595120064b56216e633224904c3e1546bf78b88b39a7c44286"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RM7YDBGQY4NWFCJKK5A2RMD52S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-Free Non-Stationary RL: Near-Optimal Regret and Applications in Multi-Agent RL and Inventory Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Simchi-Levi, Kaiqing Zhang, Ruihao Zhu, Tamer Ba\\c{s}ar, Weichao Mao","submitted_at":"2020-10-07T04:55:56Z","abstract_excerpt":"We consider model-free reinforcement learning (RL) in non-stationary Markov decision processes. Both the reward functions and the state transition functions are allowed to vary arbitrarily over time as long as their cumulative variations do not exceed certain variation budgets. We propose Restarted Q-Learning with Upper Confidence Bounds (RestartQ-UCB), the first model-free algorithm for non-stationary RL, and show that it outperforms existing solutions in terms of dynamic regret. Specifically, RestartQ-UCB with Freedman-type bonus terms achieves a dynamic regret bound of $\\widetilde{O}(S^{\\fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03161","kind":"arxiv","version":4},"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/2010.03161/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":"2026-07-05T04:50:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M97WeBCFirk47KuyegMffvE0WfluTdeGMXlcxbMuzaEOrIzrrT5AfPT2lv7MKx1M/n2VDf1g9OkCbF8xHmVmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:28:48.094694Z"},"content_sha256":"9b5ff4f0064d489ca2f408d4b82beff0da1d4d1511dd146c444ddc7c34c70003","schema_version":"1.0","event_id":"sha256:9b5ff4f0064d489ca2f408d4b82beff0da1d4d1511dd146c444ddc7c34c70003"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RM7YDBGQY4NWFCJKK5A2RMD52S/bundle.json","state_url":"https://pith.science/pith/RM7YDBGQY4NWFCJKK5A2RMD52S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RM7YDBGQY4NWFCJKK5A2RMD52S/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":"2026-08-09T10:28:48Z","links":{"resolver":"https://pith.science/pith/RM7YDBGQY4NWFCJKK5A2RMD52S","bundle":"https://pith.science/pith/RM7YDBGQY4NWFCJKK5A2RMD52S/bundle.json","state":"https://pith.science/pith/RM7YDBGQY4NWFCJKK5A2RMD52S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RM7YDBGQY4NWFCJKK5A2RMD52S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RM7YDBGQY4NWFCJKK5A2RMD52S","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":"7d01d3acf330a29f0292cd8d24c454815821b8057ad6b8837c0b9bcd432defa6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T04:55:56Z","title_canon_sha256":"02e875b3a3aa36a2cd93927d8b05e2d8109b4b8facc576171b9ffa6f7d934cbd"},"schema_version":"1.0","source":{"id":"2010.03161","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.03161","created_at":"2026-07-05T04:50:00Z"},{"alias_kind":"arxiv_version","alias_value":"2010.03161v4","created_at":"2026-07-05T04:50:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03161","created_at":"2026-07-05T04:50:00Z"},{"alias_kind":"pith_short_12","alias_value":"RM7YDBGQY4NW","created_at":"2026-07-05T04:50:00Z"},{"alias_kind":"pith_short_16","alias_value":"RM7YDBGQY4NWFCJK","created_at":"2026-07-05T04:50:00Z"},{"alias_kind":"pith_short_8","alias_value":"RM7YDBGQ","created_at":"2026-07-05T04:50:00Z"}],"graph_snapshots":[{"event_id":"sha256:9b5ff4f0064d489ca2f408d4b82beff0da1d4d1511dd146c444ddc7c34c70003","target":"graph","created_at":"2026-07-05T04:50:00Z","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/2010.03161/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider model-free reinforcement learning (RL) in non-stationary Markov decision processes. Both the reward functions and the state transition functions are allowed to vary arbitrarily over time as long as their cumulative variations do not exceed certain variation budgets. We propose Restarted Q-Learning with Upper Confidence Bounds (RestartQ-UCB), the first model-free algorithm for non-stationary RL, and show that it outperforms existing solutions in terms of dynamic regret. Specifically, RestartQ-UCB with Freedman-type bonus terms achieves a dynamic regret bound of $\\widetilde{O}(S^{\\fr","authors_text":"David Simchi-Levi, Kaiqing Zhang, Ruihao Zhu, Tamer Ba\\c{s}ar, Weichao Mao","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T04:55:56Z","title":"Model-Free Non-Stationary RL: Near-Optimal Regret and Applications in Multi-Agent RL and Inventory Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03161","kind":"arxiv","version":4},"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":"sha256:783ac0d2d89cb7595120064b56216e633224904c3e1546bf78b88b39a7c44286","target":"record","created_at":"2026-07-05T04:50:00Z","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":"7d01d3acf330a29f0292cd8d24c454815821b8057ad6b8837c0b9bcd432defa6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T04:55:56Z","title_canon_sha256":"02e875b3a3aa36a2cd93927d8b05e2d8109b4b8facc576171b9ffa6f7d934cbd"},"schema_version":"1.0","source":{"id":"2010.03161","kind":"arxiv","version":4}},"canonical_sha256":"8b3f8184d0c71b62892a5741a8b07dd4a4b7695df21548360f16f33d98dab366","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b3f8184d0c71b62892a5741a8b07dd4a4b7695df21548360f16f33d98dab366","first_computed_at":"2026-07-05T04:50:00.695124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:50:00.695124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d0+wudYJBmo/l+9lQKCGxjR2hi2reO3CWlh+03+V1Nrvgy3xxJ+Le0JkvgYF9V8FR485IPSAamJdBoLCkMvNDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:50:00.695798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.03161","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:783ac0d2d89cb7595120064b56216e633224904c3e1546bf78b88b39a7c44286","sha256:9b5ff4f0064d489ca2f408d4b82beff0da1d4d1511dd146c444ddc7c34c70003"],"state_sha256":"7cd7b9e51b2739444506232d63f74afa1a94e0b4206833d96a277fa5e770c796"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FFtyWTFyqc/6976izlZB3kpJ0QuAEwHARkKvzyL/tzgydSkR0MLPD52T6LVGyMi2HeOmPhQOBPRfW61EYc2ICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T10:28:48.098857Z","bundle_sha256":"ebc7471c286ae42929c64607ec7f87a0b6c486fbcd88659ee3728de70f5cca8a"}}