{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:DRC3WXPWTWAZSYGRVSWW5YYQNV","short_pith_number":"pith:DRC3WXPW","schema_version":"1.0","canonical_sha256":"1c45bb5df69d819960d1acad6ee3106d66375f1e602188059260e605116c3ed8","source":{"kind":"arxiv","id":"1610.09512","version":2},"attestation_state":"computed","paper":{"title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Alekh Agarwal, John Langford, Nan Jiang, Robert E. Schapire","submitted_at":"2016-10-29T14:01:58Z","abstract_excerpt":"This paper studies systematic exploration for reinforcement learning with rich observations and function approximation. We introduce a new model called contextual decision processes, that unifies and generalizes most prior settings. Our first contribution is a complexity measure, the Bellman rank, that we show enables tractable learning of near-optimal behavior in these processes and is naturally small for many well-studied reinforcement learning settings. Our second contribution is a new reinforcement learning algorithm that engages in systematic exploration to learn contextual decision proce"},"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":"1610.09512","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-29T14:01:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4c7ae114fc0539c8f8036e6c958de287223885c61a83c8fa1ec13e1682ad2e41","abstract_canon_sha256":"c51676d578450cb60ce7efc926d78f3283f06c3cdd70215fba08934772e7ae88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:06.030071Z","signature_b64":"PgQxBLr4dRXhMu/0x8R28bMsANu56D1irCvCXSQZ4wYT+xoTOhLusJCWtCPkfxjaeCGfhcUYiiL/3zb2gBtQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c45bb5df69d819960d1acad6ee3106d66375f1e602188059260e605116c3ed8","last_reissued_at":"2026-05-18T00:56:06.029401Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:06.029401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Decision Processes with Low Bellman Rank are PAC-Learnable","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Alekh Agarwal, John Langford, Nan Jiang, Robert E. Schapire","submitted_at":"2016-10-29T14:01:58Z","abstract_excerpt":"This paper studies systematic exploration for reinforcement learning with rich observations and function approximation. We introduce a new model called contextual decision processes, that unifies and generalizes most prior settings. Our first contribution is a complexity measure, the Bellman rank, that we show enables tractable learning of near-optimal behavior in these processes and is naturally small for many well-studied reinforcement learning settings. Our second contribution is a new reinforcement learning algorithm that engages in systematic exploration to learn contextual decision proce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09512","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":"1610.09512","created_at":"2026-05-18T00:56:06.029521+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.09512v2","created_at":"2026-05-18T00:56:06.029521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09512","created_at":"2026-05-18T00:56:06.029521+00:00"},{"alias_kind":"pith_short_12","alias_value":"DRC3WXPWTWAZ","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_16","alias_value":"DRC3WXPWTWAZSYGR","created_at":"2026-05-18T12:30:12.583610+00:00"},{"alias_kind":"pith_short_8","alias_value":"DRC3WXPW","created_at":"2026-05-18T12:30:12.583610+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/DRC3WXPWTWAZSYGRVSWW5YYQNV","json":"https://pith.science/pith/DRC3WXPWTWAZSYGRVSWW5YYQNV.json","graph_json":"https://pith.science/api/pith-number/DRC3WXPWTWAZSYGRVSWW5YYQNV/graph.json","events_json":"https://pith.science/api/pith-number/DRC3WXPWTWAZSYGRVSWW5YYQNV/events.json","paper":"https://pith.science/paper/DRC3WXPW"},"agent_actions":{"view_html":"https://pith.science/pith/DRC3WXPWTWAZSYGRVSWW5YYQNV","download_json":"https://pith.science/pith/DRC3WXPWTWAZSYGRVSWW5YYQNV.json","view_paper":"https://pith.science/paper/DRC3WXPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.09512&json=true","fetch_graph":"https://pith.science/api/pith-number/DRC3WXPWTWAZSYGRVSWW5YYQNV/graph.json","fetch_events":"https://pith.science/api/pith-number/DRC3WXPWTWAZSYGRVSWW5YYQNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DRC3WXPWTWAZSYGRVSWW5YYQNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DRC3WXPWTWAZSYGRVSWW5YYQNV/action/storage_attestation","attest_author":"https://pith.science/pith/DRC3WXPWTWAZSYGRVSWW5YYQNV/action/author_attestation","sign_citation":"https://pith.science/pith/DRC3WXPWTWAZSYGRVSWW5YYQNV/action/citation_signature","submit_replication":"https://pith.science/pith/DRC3WXPWTWAZSYGRVSWW5YYQNV/action/replication_record"}},"created_at":"2026-05-18T00:56:06.029521+00:00","updated_at":"2026-05-18T00:56:06.029521+00:00"}