{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GZRNLV5RIFPQI7BWFP6TOXE5QJ","short_pith_number":"pith:GZRNLV5R","canonical_record":{"source":{"id":"2010.12870","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T11:02:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fe548858f15e6597e74450e6882db8ee6a45e9458b736397fbde89628e711981","abstract_canon_sha256":"9cafe0a9c2f10fa8259b7e8a738148280b24591f5883acf52b5d4f6098ea952d"},"schema_version":"1.0"},"canonical_sha256":"3662d5d7b1415f047c362bfd375c9d824af2d374a96d2285479c7844e8d9cc75","source":{"kind":"arxiv","id":"2010.12870","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12870","created_at":"2026-07-05T03:43:37Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12870v3","created_at":"2026-07-05T03:43:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12870","created_at":"2026-07-05T03:43:37Z"},{"alias_kind":"pith_short_12","alias_value":"GZRNLV5RIFPQ","created_at":"2026-07-05T03:43:37Z"},{"alias_kind":"pith_short_16","alias_value":"GZRNLV5RIFPQI7BW","created_at":"2026-07-05T03:43:37Z"},{"alias_kind":"pith_short_8","alias_value":"GZRNLV5R","created_at":"2026-07-05T03:43:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GZRNLV5RIFPQI7BWFP6TOXE5QJ","target":"record","payload":{"canonical_record":{"source":{"id":"2010.12870","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T11:02:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fe548858f15e6597e74450e6882db8ee6a45e9458b736397fbde89628e711981","abstract_canon_sha256":"9cafe0a9c2f10fa8259b7e8a738148280b24591f5883acf52b5d4f6098ea952d"},"schema_version":"1.0"},"canonical_sha256":"3662d5d7b1415f047c362bfd375c9d824af2d374a96d2285479c7844e8d9cc75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:37.498401Z","signature_b64":"bDl+zfxEwx+A7MIfE2vDYHl6mUVu6Qub9lw7RYfXdWJSK4WLTL1nOjbtafEoyT+TIeLGf955QmUnEMZ53otKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3662d5d7b1415f047c362bfd375c9d824af2d374a96d2285479c7844e8d9cc75","last_reissued_at":"2026-07-05T03:43:37.497994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:37.497994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.12870","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":"2026-07-05T03:43:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ii7gkQ3ctoJRc78L7FH//oGdErEZhT9i+OE+cJYmXVbN1o6Uloiqj8pZamS6zlfxcDdxmwmadiY7pjnymreEDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:32:32.600190Z"},"content_sha256":"e6e78976b082b3efa58a8cf4a5a9f4959899826215a318f642f68049eff760fb","schema_version":"1.0","event_id":"sha256:e6e78976b082b3efa58a8cf4a5a9f4959899826215a318f642f68049eff760fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GZRNLV5RIFPQI7BWFP6TOXE5QJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Learning in Non-Stationary Linear Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Touati, Pascal Vincent","submitted_at":"2020-10-24T11:02:45Z","abstract_excerpt":"We study episodic reinforcement learning in non-stationary linear (a.k.a. low-rank) Markov Decision Processes (MDPs), i.e, both the reward and transition kernel are linear with respect to a given feature map and are allowed to evolve either slowly or abruptly over time. For this problem setting, we propose OPT-WLSVI an optimistic model-free algorithm based on weighted least squares value iteration which uses exponential weights to smoothly forget data that are far in the past. We show that our algorithm, when competing against the best policy at each time, achieves a regret that is upper bound"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12870","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/2010.12870/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":"2026-07-05T03:43:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O+Rwql5Nhu4GllocCqpZmAX7fVitzkOO6PIrMpRSZ0q3BWYtprAp3QHAydZbCzZgVBX+rlFXmua+MyyWMII0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T18:32:32.600702Z"},"content_sha256":"72ba5d00604cd2e7b411e176db46935557baf3ce9e3d82b9d1c3df373b38732b","schema_version":"1.0","event_id":"sha256:72ba5d00604cd2e7b411e176db46935557baf3ce9e3d82b9d1c3df373b38732b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GZRNLV5RIFPQI7BWFP6TOXE5QJ/bundle.json","state_url":"https://pith.science/pith/GZRNLV5RIFPQI7BWFP6TOXE5QJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GZRNLV5RIFPQI7BWFP6TOXE5QJ/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":"2026-08-05T18:32:32Z","links":{"resolver":"https://pith.science/pith/GZRNLV5RIFPQI7BWFP6TOXE5QJ","bundle":"https://pith.science/pith/GZRNLV5RIFPQI7BWFP6TOXE5QJ/bundle.json","state":"https://pith.science/pith/GZRNLV5RIFPQI7BWFP6TOXE5QJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GZRNLV5RIFPQI7BWFP6TOXE5QJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GZRNLV5RIFPQI7BWFP6TOXE5QJ","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":"9cafe0a9c2f10fa8259b7e8a738148280b24591f5883acf52b5d4f6098ea952d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T11:02:45Z","title_canon_sha256":"fe548858f15e6597e74450e6882db8ee6a45e9458b736397fbde89628e711981"},"schema_version":"1.0","source":{"id":"2010.12870","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12870","created_at":"2026-07-05T03:43:37Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12870v3","created_at":"2026-07-05T03:43:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12870","created_at":"2026-07-05T03:43:37Z"},{"alias_kind":"pith_short_12","alias_value":"GZRNLV5RIFPQ","created_at":"2026-07-05T03:43:37Z"},{"alias_kind":"pith_short_16","alias_value":"GZRNLV5RIFPQI7BW","created_at":"2026-07-05T03:43:37Z"},{"alias_kind":"pith_short_8","alias_value":"GZRNLV5R","created_at":"2026-07-05T03:43:37Z"}],"graph_snapshots":[{"event_id":"sha256:72ba5d00604cd2e7b411e176db46935557baf3ce9e3d82b9d1c3df373b38732b","target":"graph","created_at":"2026-07-05T03:43:37Z","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/2010.12870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study episodic reinforcement learning in non-stationary linear (a.k.a. low-rank) Markov Decision Processes (MDPs), i.e, both the reward and transition kernel are linear with respect to a given feature map and are allowed to evolve either slowly or abruptly over time. For this problem setting, we propose OPT-WLSVI an optimistic model-free algorithm based on weighted least squares value iteration which uses exponential weights to smoothly forget data that are far in the past. We show that our algorithm, when competing against the best policy at each time, achieves a regret that is upper bound","authors_text":"Ahmed Touati, Pascal Vincent","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T11:02:45Z","title":"Efficient Learning in Non-Stationary Linear Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12870","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:e6e78976b082b3efa58a8cf4a5a9f4959899826215a318f642f68049eff760fb","target":"record","created_at":"2026-07-05T03:43:37Z","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":"9cafe0a9c2f10fa8259b7e8a738148280b24591f5883acf52b5d4f6098ea952d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T11:02:45Z","title_canon_sha256":"fe548858f15e6597e74450e6882db8ee6a45e9458b736397fbde89628e711981"},"schema_version":"1.0","source":{"id":"2010.12870","kind":"arxiv","version":3}},"canonical_sha256":"3662d5d7b1415f047c362bfd375c9d824af2d374a96d2285479c7844e8d9cc75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3662d5d7b1415f047c362bfd375c9d824af2d374a96d2285479c7844e8d9cc75","first_computed_at":"2026-07-05T03:43:37.497994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:43:37.497994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bDl+zfxEwx+A7MIfE2vDYHl6mUVu6Qub9lw7RYfXdWJSK4WLTL1nOjbtafEoyT+TIeLGf955QmUnEMZ53otKDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:43:37.498401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12870","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6e78976b082b3efa58a8cf4a5a9f4959899826215a318f642f68049eff760fb","sha256:72ba5d00604cd2e7b411e176db46935557baf3ce9e3d82b9d1c3df373b38732b"],"state_sha256":"6fadc9cbc0f6bc1c427e8a6b1450270b2b9c8cd73e3efe4035bc00c5a87a4c62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KHwD42729JMGYyH2nALsa7nfx8Lp8BAWMSCjK7yJ6L/6OhJDt1KJ3V7A+D3Jch5xCwmWU2F3WWMSCjzhodMyCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T18:32:32.604887Z","bundle_sha256":"c46909320bc17dd05435f1d24695e98bbf056874c27bd2d096c21aefea8bbe55"}}