{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:NEGSK7ZL4ATJ77HLKD4QE54LIA","short_pith_number":"pith:NEGSK7ZL","schema_version":"1.0","canonical_sha256":"690d257f2be0269ffceb50f902778b400fec27ebbdca1c380c9ddf8a76721153","source":{"kind":"arxiv","id":"1406.7498","version":3},"attestation_state":"computed","paper":{"title":"Thompson Sampling for Learning Parameterized Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aditya Gopalan, Shie Mannor","submitted_at":"2014-06-29T12:34:45Z","abstract_excerpt":"We consider reinforcement learning in parameterized Markov Decision Processes (MDPs), where the parameterization may induce correlation across transition probabilities or rewards. Consequently, observing a particular state transition might yield useful information about other, unobserved, parts of the MDP. We present a version of Thompson sampling for parameterized reinforcement learning problems, and derive a frequentist regret bound for priors over general parameter spaces. The result shows that the number of instants where suboptimal actions are chosen scales logarithmically with time, with"},"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":"1406.7498","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-06-29T12:34:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"05ed705e6df60156ef646c05092b04891f3438495bf2d62d28ad7e4eb165ee5a","abstract_canon_sha256":"0cdd9cd915ea3cf68b82c5fad200589a9f7ede1da3a4ee5b0af2b390f4e211d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:59.908008Z","signature_b64":"qEP155tXL5WicQQK0/wjxQ5RTAFwFyxnJcC8id0G8rd4sDPBZdZiUCpN1qsmJmub3fRTXYmR9pGSX7GmtW8jCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"690d257f2be0269ffceb50f902778b400fec27ebbdca1c380c9ddf8a76721153","last_reissued_at":"2026-05-18T02:19:59.907260Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:59.907260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thompson Sampling for Learning Parameterized Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aditya Gopalan, Shie Mannor","submitted_at":"2014-06-29T12:34:45Z","abstract_excerpt":"We consider reinforcement learning in parameterized Markov Decision Processes (MDPs), where the parameterization may induce correlation across transition probabilities or rewards. Consequently, observing a particular state transition might yield useful information about other, unobserved, parts of the MDP. We present a version of Thompson sampling for parameterized reinforcement learning problems, and derive a frequentist regret bound for priors over general parameter spaces. The result shows that the number of instants where suboptimal actions are chosen scales logarithmically with time, with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.7498","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":""},"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":"1406.7498","created_at":"2026-05-18T02:19:59.907399+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.7498v3","created_at":"2026-05-18T02:19:59.907399+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.7498","created_at":"2026-05-18T02:19:59.907399+00:00"},{"alias_kind":"pith_short_12","alias_value":"NEGSK7ZL4ATJ","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_16","alias_value":"NEGSK7ZL4ATJ77HL","created_at":"2026-05-18T12:28:41.024544+00:00"},{"alias_kind":"pith_short_8","alias_value":"NEGSK7ZL","created_at":"2026-05-18T12:28:41.024544+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/NEGSK7ZL4ATJ77HLKD4QE54LIA","json":"https://pith.science/pith/NEGSK7ZL4ATJ77HLKD4QE54LIA.json","graph_json":"https://pith.science/api/pith-number/NEGSK7ZL4ATJ77HLKD4QE54LIA/graph.json","events_json":"https://pith.science/api/pith-number/NEGSK7ZL4ATJ77HLKD4QE54LIA/events.json","paper":"https://pith.science/paper/NEGSK7ZL"},"agent_actions":{"view_html":"https://pith.science/pith/NEGSK7ZL4ATJ77HLKD4QE54LIA","download_json":"https://pith.science/pith/NEGSK7ZL4ATJ77HLKD4QE54LIA.json","view_paper":"https://pith.science/paper/NEGSK7ZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.7498&json=true","fetch_graph":"https://pith.science/api/pith-number/NEGSK7ZL4ATJ77HLKD4QE54LIA/graph.json","fetch_events":"https://pith.science/api/pith-number/NEGSK7ZL4ATJ77HLKD4QE54LIA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NEGSK7ZL4ATJ77HLKD4QE54LIA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NEGSK7ZL4ATJ77HLKD4QE54LIA/action/storage_attestation","attest_author":"https://pith.science/pith/NEGSK7ZL4ATJ77HLKD4QE54LIA/action/author_attestation","sign_citation":"https://pith.science/pith/NEGSK7ZL4ATJ77HLKD4QE54LIA/action/citation_signature","submit_replication":"https://pith.science/pith/NEGSK7ZL4ATJ77HLKD4QE54LIA/action/replication_record"}},"created_at":"2026-05-18T02:19:59.907399+00:00","updated_at":"2026-05-18T02:19:59.907399+00:00"}