{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AQJ25OP3VGPKMPW5224DY2Q3WW","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":"196ebf0f2a1bd34a06399ae9e9c3781ebd70f86fe871a76859a16288a052032c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-25T10:14:20Z","title_canon_sha256":"51b6670f8eee2e86be2792665078e6352e08d711f12884f9973b2a4378b35e7f"},"schema_version":"1.0","source":{"id":"1805.10066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.10066","created_at":"2026-05-18T00:14:58Z"},{"alias_kind":"arxiv_version","alias_value":"1805.10066v1","created_at":"2026-05-18T00:14:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.10066","created_at":"2026-05-18T00:14:58Z"},{"alias_kind":"pith_short_12","alias_value":"AQJ25OP3VGPK","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AQJ25OP3VGPKMPW5","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AQJ25OP3","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:0266cc070494e46ea26922d6ccdba3682a6f9b7157098a3ad66cf319194ad214","target":"graph","created_at":"2026-05-18T00:14:58Z","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"},"paper":{"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","authors_text":"Peter Auer, Pratik Gajane, Ronald Ortner","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-25T10:14:20Z","title":"A Sliding-Window Algorithm for Markov Decision Processes with Arbitrarily Changing Rewards and Transitions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.10066","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:c7e0116813d788dbd33e1d292967ca2a386866ae4bf51f9e50e90a3b2e5811d7","target":"record","created_at":"2026-05-18T00:14:58Z","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":"196ebf0f2a1bd34a06399ae9e9c3781ebd70f86fe871a76859a16288a052032c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-25T10:14:20Z","title_canon_sha256":"51b6670f8eee2e86be2792665078e6352e08d711f12884f9973b2a4378b35e7f"},"schema_version":"1.0","source":{"id":"1805.10066","kind":"arxiv","version":1}},"canonical_sha256":"0413aeb9fba99ea63eddd6b83c6a1bb5ac42a1d2fece02ca1eaa721b14dfa8ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0413aeb9fba99ea63eddd6b83c6a1bb5ac42a1d2fece02ca1eaa721b14dfa8ed","first_computed_at":"2026-05-18T00:14:58.367033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:58.367033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uzjzh8A8YAHwmTl5ikfhk5SyzyFIDwdo/WmnwutTpn6UhHbfGMlQ24xN5Reig8+U7OOvDRZMshzZKc9Ay4AMBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:58.367600Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.10066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7e0116813d788dbd33e1d292967ca2a386866ae4bf51f9e50e90a3b2e5811d7","sha256:0266cc070494e46ea26922d6ccdba3682a6f9b7157098a3ad66cf319194ad214"],"state_sha256":"5fa5ea137c7760e3e4f27d007cf348ff89892017c8f7e6b5c3005e10f6cb438e"}