{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:H65HPER5RC6AS5UJ7LF4K7PRN6","short_pith_number":"pith:H65HPER5","schema_version":"1.0","canonical_sha256":"3fba77923d88bc097689facbc57df16fa222d1521440617b3a452a895ed1a65f","source":{"kind":"arxiv","id":"1803.00606","version":4},"attestation_state":"computed","paper":{"title":"On Oracle-Efficient PAC RL with Rich Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Alekh Agarwal, Christoph Dann, John Langford, Nan Jiang, Robert E. Schapire","submitted_at":"2018-03-01T20:08:06Z","abstract_excerpt":"We study the computational tractability of PAC reinforcement learning with rich observations. We present new provably sample-efficient algorithms for environments with deterministic hidden state dynamics and stochastic rich observations. These methods operate in an oracle model of computation -- accessing policy and value function classes exclusively through standard optimization primitives -- and therefore represent computationally efficient alternatives to prior algorithms that require enumeration. With stochastic hidden state dynamics, we prove that the only known sample-efficient algorithm"},"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":"1803.00606","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-01T20:08:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bcbc17206465ebf0c07f85f31473a1218a378610f19538f7d7f3af7a59dea247","abstract_canon_sha256":"1c41eff31933f18a38c77c80e4f832bae4879152d8794f3f212b3a2e3e195c88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:10.297168Z","signature_b64":"yZpLmnDhphlsa3ijRcVPXKxK9BfBfaWBZH2fHChlWtrRL4aUmKXKqIxwi6LfmrCFGNo+n2v9DxN/6M+L5jHzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fba77923d88bc097689facbc57df16fa222d1521440617b3a452a895ed1a65f","last_reissued_at":"2026-05-17T23:56:10.296489Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:10.296489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Oracle-Efficient PAC RL with Rich Observations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Alekh Agarwal, Christoph Dann, John Langford, Nan Jiang, Robert E. Schapire","submitted_at":"2018-03-01T20:08:06Z","abstract_excerpt":"We study the computational tractability of PAC reinforcement learning with rich observations. We present new provably sample-efficient algorithms for environments with deterministic hidden state dynamics and stochastic rich observations. These methods operate in an oracle model of computation -- accessing policy and value function classes exclusively through standard optimization primitives -- and therefore represent computationally efficient alternatives to prior algorithms that require enumeration. With stochastic hidden state dynamics, we prove that the only known sample-efficient algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00606","kind":"arxiv","version":4},"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":"1803.00606","created_at":"2026-05-17T23:56:10.296597+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.00606v4","created_at":"2026-05-17T23:56:10.296597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00606","created_at":"2026-05-17T23:56:10.296597+00:00"},{"alias_kind":"pith_short_12","alias_value":"H65HPER5RC6A","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"H65HPER5RC6AS5UJ","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"H65HPER5","created_at":"2026-05-18T12:32:28.185984+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/H65HPER5RC6AS5UJ7LF4K7PRN6","json":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6.json","graph_json":"https://pith.science/api/pith-number/H65HPER5RC6AS5UJ7LF4K7PRN6/graph.json","events_json":"https://pith.science/api/pith-number/H65HPER5RC6AS5UJ7LF4K7PRN6/events.json","paper":"https://pith.science/paper/H65HPER5"},"agent_actions":{"view_html":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6","download_json":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6.json","view_paper":"https://pith.science/paper/H65HPER5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.00606&json=true","fetch_graph":"https://pith.science/api/pith-number/H65HPER5RC6AS5UJ7LF4K7PRN6/graph.json","fetch_events":"https://pith.science/api/pith-number/H65HPER5RC6AS5UJ7LF4K7PRN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6/action/storage_attestation","attest_author":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6/action/author_attestation","sign_citation":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6/action/citation_signature","submit_replication":"https://pith.science/pith/H65HPER5RC6AS5UJ7LF4K7PRN6/action/replication_record"}},"created_at":"2026-05-17T23:56:10.296597+00:00","updated_at":"2026-05-17T23:56:10.296597+00:00"}