{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:NA4F4LYNA2HCOGZCJDNHHKF6DF","short_pith_number":"pith:NA4F4LYN","schema_version":"1.0","canonical_sha256":"68385e2f0d068e271b2248da73a8be195803a07804da90ff7884a9ab100dae5b","source":{"kind":"arxiv","id":"1302.2553","version":2},"attestation_state":"computed","paper":{"title":"Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniil Ryabko, Odalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner","submitted_at":"2013-02-11T17:55:49Z","abstract_excerpt":"We consider an agent interacting with an environment in a single stream of actions, observations, and rewards, with no reset. This process is not assumed to be a Markov Decision Process (MDP). Rather, the agent has several representations (mapping histories of past interactions to a discrete state space) of the environment with unknown dynamics, only some of which result in an MDP. The goal is to minimize the average regret criterion against an agent who knows an MDP representation giving the highest optimal reward, and acts optimally in it. Recent regret bounds for this setting are of order $"},"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":"1302.2553","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-02-11T17:55:49Z","cross_cats_sorted":[],"title_canon_sha256":"2d742d9fbc4fb105867bcfd5219ff4f7134f35ba8892d745055393cde755b67c","abstract_canon_sha256":"b4a531352bc56c436d51f3192b46b3963f1dd5cb5fb64c469396e7a5715c04b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:30:40.890977Z","signature_b64":"2rLem/7eeGgOUFLNvHmcm9sUUFKUeUAuv7B02Ypc0ZFqu0W7wPhbws+1DKfs+tEZ5zVBYW0xEBUepNSiVbEVCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68385e2f0d068e271b2248da73a8be195803a07804da90ff7884a9ab100dae5b","last_reissued_at":"2026-05-18T03:30:40.890135Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:30:40.890135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniil Ryabko, Odalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner","submitted_at":"2013-02-11T17:55:49Z","abstract_excerpt":"We consider an agent interacting with an environment in a single stream of actions, observations, and rewards, with no reset. This process is not assumed to be a Markov Decision Process (MDP). Rather, the agent has several representations (mapping histories of past interactions to a discrete state space) of the environment with unknown dynamics, only some of which result in an MDP. The goal is to minimize the average regret criterion against an agent who knows an MDP representation giving the highest optimal reward, and acts optimally in it. Recent regret bounds for this setting are of order $"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1302.2553","kind":"arxiv","version":2},"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":"1302.2553","created_at":"2026-05-18T03:30:40.890283+00:00"},{"alias_kind":"arxiv_version","alias_value":"1302.2553v2","created_at":"2026-05-18T03:30:40.890283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1302.2553","created_at":"2026-05-18T03:30:40.890283+00:00"},{"alias_kind":"pith_short_12","alias_value":"NA4F4LYNA2HC","created_at":"2026-05-18T12:27:52.871228+00:00"},{"alias_kind":"pith_short_16","alias_value":"NA4F4LYNA2HCOGZC","created_at":"2026-05-18T12:27:52.871228+00:00"},{"alias_kind":"pith_short_8","alias_value":"NA4F4LYN","created_at":"2026-05-18T12:27:52.871228+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/NA4F4LYNA2HCOGZCJDNHHKF6DF","json":"https://pith.science/pith/NA4F4LYNA2HCOGZCJDNHHKF6DF.json","graph_json":"https://pith.science/api/pith-number/NA4F4LYNA2HCOGZCJDNHHKF6DF/graph.json","events_json":"https://pith.science/api/pith-number/NA4F4LYNA2HCOGZCJDNHHKF6DF/events.json","paper":"https://pith.science/paper/NA4F4LYN"},"agent_actions":{"view_html":"https://pith.science/pith/NA4F4LYNA2HCOGZCJDNHHKF6DF","download_json":"https://pith.science/pith/NA4F4LYNA2HCOGZCJDNHHKF6DF.json","view_paper":"https://pith.science/paper/NA4F4LYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1302.2553&json=true","fetch_graph":"https://pith.science/api/pith-number/NA4F4LYNA2HCOGZCJDNHHKF6DF/graph.json","fetch_events":"https://pith.science/api/pith-number/NA4F4LYNA2HCOGZCJDNHHKF6DF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NA4F4LYNA2HCOGZCJDNHHKF6DF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NA4F4LYNA2HCOGZCJDNHHKF6DF/action/storage_attestation","attest_author":"https://pith.science/pith/NA4F4LYNA2HCOGZCJDNHHKF6DF/action/author_attestation","sign_citation":"https://pith.science/pith/NA4F4LYNA2HCOGZCJDNHHKF6DF/action/citation_signature","submit_replication":"https://pith.science/pith/NA4F4LYNA2HCOGZCJDNHHKF6DF/action/replication_record"}},"created_at":"2026-05-18T03:30:40.890283+00:00","updated_at":"2026-05-18T03:30:40.890283+00:00"}