{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AQJ25OP3VGPKMPW5224DY2Q3WW","short_pith_number":"pith:AQJ25OP3","schema_version":"1.0","canonical_sha256":"0413aeb9fba99ea63eddd6b83c6a1bb5ac42a1d2fece02ca1eaa721b14dfa8ed","source":{"kind":"arxiv","id":"1805.10066","version":1},"attestation_state":"computed","paper":{"title":"A Sliding-Window Algorithm for Markov Decision Processes with Arbitrarily Changing Rewards and Transitions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Peter Auer, Pratik Gajane, Ronald Ortner","submitted_at":"2018-05-25T10:14:20Z","abstract_excerpt":"We consider reinforcement learning in changing Markov Decision Processes where both the state-transition probabilities and the reward functions may vary over time. For this problem setting, we propose an algorithm using a sliding window approach and provide performance guarantees for the regret evaluated against the optimal non-stationary policy. We also characterize the optimal window size suitable for our algorithm. These results are complemented by a sample complexity bound on the number of sub-optimal steps taken by the algorithm. Finally, we present some experimental results to support ou"},"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":"1805.10066","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-25T10:14:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"51b6670f8eee2e86be2792665078e6352e08d711f12884f9973b2a4378b35e7f","abstract_canon_sha256":"196ebf0f2a1bd34a06399ae9e9c3781ebd70f86fe871a76859a16288a052032c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:58.367600Z","signature_b64":"Uzjzh8A8YAHwmTl5ikfhk5SyzyFIDwdo/WmnwutTpn6UhHbfGMlQ24xN5Reig8+U7OOvDRZMshzZKc9Ay4AMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0413aeb9fba99ea63eddd6b83c6a1bb5ac42a1d2fece02ca1eaa721b14dfa8ed","last_reissued_at":"2026-05-18T00:14:58.367033Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:58.367033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Sliding-Window Algorithm for Markov Decision Processes with Arbitrarily Changing Rewards and Transitions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Peter Auer, Pratik Gajane, Ronald Ortner","submitted_at":"2018-05-25T10:14:20Z","abstract_excerpt":"We consider reinforcement learning in changing Markov Decision Processes where both the state-transition probabilities and the reward functions may vary over time. For this problem setting, we propose an algorithm using a sliding window approach and provide performance guarantees for the regret evaluated against the optimal non-stationary policy. We also characterize the optimal window size suitable for our algorithm. These results are complemented by a sample complexity bound on the number of sub-optimal steps taken by the algorithm. Finally, we present some experimental results to support ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10066","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1805.10066","created_at":"2026-05-18T00:14:58.367135+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.10066v1","created_at":"2026-05-18T00:14:58.367135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10066","created_at":"2026-05-18T00:14:58.367135+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQJ25OP3VGPK","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQJ25OP3VGPKMPW5","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQJ25OP3","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQJ25OP3VGPKMPW5224DY2Q3WW","json":"https://pith.science/pith/AQJ25OP3VGPKMPW5224DY2Q3WW.json","graph_json":"https://pith.science/api/pith-number/AQJ25OP3VGPKMPW5224DY2Q3WW/graph.json","events_json":"https://pith.science/api/pith-number/AQJ25OP3VGPKMPW5224DY2Q3WW/events.json","paper":"https://pith.science/paper/AQJ25OP3"},"agent_actions":{"view_html":"https://pith.science/pith/AQJ25OP3VGPKMPW5224DY2Q3WW","download_json":"https://pith.science/pith/AQJ25OP3VGPKMPW5224DY2Q3WW.json","view_paper":"https://pith.science/paper/AQJ25OP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.10066&json=true","fetch_graph":"https://pith.science/api/pith-number/AQJ25OP3VGPKMPW5224DY2Q3WW/graph.json","fetch_events":"https://pith.science/api/pith-number/AQJ25OP3VGPKMPW5224DY2Q3WW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQJ25OP3VGPKMPW5224DY2Q3WW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQJ25OP3VGPKMPW5224DY2Q3WW/action/storage_attestation","attest_author":"https://pith.science/pith/AQJ25OP3VGPKMPW5224DY2Q3WW/action/author_attestation","sign_citation":"https://pith.science/pith/AQJ25OP3VGPKMPW5224DY2Q3WW/action/citation_signature","submit_replication":"https://pith.science/pith/AQJ25OP3VGPKMPW5224DY2Q3WW/action/replication_record"}},"created_at":"2026-05-18T00:14:58.367135+00:00","updated_at":"2026-05-18T00:14:58.367135+00:00"}