{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:R7S3XPRYLUNV27WOLK3WGHML7V","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":"7dcd4820167cefd5bee290ed0eed3605d2576ddda3dfdcc350e3a6b853ddb3bb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-08-04T01:52:42Z","title_canon_sha256":"10c4681b504aed038ee085f830287a69acd9113b0c6d41b731c66089df57eeff"},"schema_version":"1.0","source":{"id":"1508.00641","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.00641","created_at":"2026-05-18T00:21:38Z"},{"alias_kind":"arxiv_version","alias_value":"1508.00641v4","created_at":"2026-05-18T00:21:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.00641","created_at":"2026-05-18T00:21:38Z"},{"alias_kind":"pith_short_12","alias_value":"R7S3XPRYLUNV","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"R7S3XPRYLUNV27WO","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"R7S3XPRY","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:2fd0a56069c15a10808f8e1b703462f7e2a73d36220e45ac6d52eb4834f8ccff","target":"graph","created_at":"2026-05-18T00:21:38Z","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 introduce a new class of reinforcement learning methods referred to as {\\em episodic multi-armed bandits} (eMAB). In eMAB the learner proceeds in {\\em episodes}, each composed of several {\\em steps}, in which it chooses an action and observes a feedback signal. Moreover, in each step, it can take a special action, called the $stop$ action, that ends the current episode. After the $stop$ action is taken, the learner collects a terminal reward, and observes the costs and terminal rewards associated with each step of the episode. The goal of the learner is to maximize its cumulative gain (i.e.","authors_text":"Cem Tekin, Mihaela van der Schaar","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-08-04T01:52:42Z","title":"Episodic Multi-armed Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.00641","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":"sha256:451c8cced943ef7ae7cc05541f5a9aba78f0638c5c1db12983178cbbf546a793","target":"record","created_at":"2026-05-18T00:21:38Z","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":"7dcd4820167cefd5bee290ed0eed3605d2576ddda3dfdcc350e3a6b853ddb3bb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-08-04T01:52:42Z","title_canon_sha256":"10c4681b504aed038ee085f830287a69acd9113b0c6d41b731c66089df57eeff"},"schema_version":"1.0","source":{"id":"1508.00641","kind":"arxiv","version":4}},"canonical_sha256":"8fe5bbbe385d1b5d7ece5ab7631d8bfd7781321a0547e82cd688b91d3dfbde91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fe5bbbe385d1b5d7ece5ab7631d8bfd7781321a0547e82cd688b91d3dfbde91","first_computed_at":"2026-05-18T00:21:38.022849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:38.022849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pCzQlpDah0Y+/H0pvgZuhziW92bwd7ZlyVOfLKbSKzcGVkCou2THEtOpvM2lynxqC50H2fmgsjsWoHxbaCnNAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:38.023478Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.00641","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:451c8cced943ef7ae7cc05541f5a9aba78f0638c5c1db12983178cbbf546a793","sha256:2fd0a56069c15a10808f8e1b703462f7e2a73d36220e45ac6d52eb4834f8ccff"],"state_sha256":"d90a275203f0a2c8ead49b723900cba093a3273dac8733126d893c09b222c4d7"}