{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2C6YWVYU5YY6WP7RCYQKCSE62U","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":"8317ca07b9340f721f34b6d4bcae4626d7348c92dfa841f8ebdbedd64d2ca683","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T13:13:01Z","title_canon_sha256":"36b85d03f531e191a28dfe12b0ead23f185009ab787b6843cf8cd495891f9804"},"schema_version":"1.0","source":{"id":"2010.05673","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.05673","created_at":"2026-07-05T01:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"2010.05673v2","created_at":"2026-07-05T01:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05673","created_at":"2026-07-05T01:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"2C6YWVYU5YY6","created_at":"2026-07-05T01:43:42Z"},{"alias_kind":"pith_short_16","alias_value":"2C6YWVYU5YY6WP7R","created_at":"2026-07-05T01:43:42Z"},{"alias_kind":"pith_short_8","alias_value":"2C6YWVYU","created_at":"2026-07-05T01:43:42Z"}],"graph_snapshots":[{"event_id":"sha256:560f5ab2d641a63b3981ef4859b5230abb82b5703083dd1dc44d331d9c70cf59","target":"graph","created_at":"2026-07-05T01:43:42Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.05673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"It is believed that a model-based approach for reinforcement learning (RL) is the key to reduce sample complexity. However, the understanding of the sample optimality of model-based RL is still largely missing, even for the linear case. This work considers sample complexity of finding an $\\epsilon$-optimal policy in a Markov decision process (MDP) that admits a linear additive feature representation, given only access to a generative model. We solve this problem via a plug-in solver approach, which builds an empirical model and plans in this empirical model via an arbitrary plug-in solver. We ","authors_text":"Lin F. Yang, Qiwen Cui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T13:13:01Z","title":"Is Plug-in Solver Sample-Efficient for Feature-based Reinforcement Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05673","kind":"arxiv","version":2},"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":"sha256:41272e006e1e897506fb61a8d474fd39c3123b2b693535531704582cbb58a490","target":"record","created_at":"2026-07-05T01:43:42Z","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":"8317ca07b9340f721f34b6d4bcae4626d7348c92dfa841f8ebdbedd64d2ca683","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T13:13:01Z","title_canon_sha256":"36b85d03f531e191a28dfe12b0ead23f185009ab787b6843cf8cd495891f9804"},"schema_version":"1.0","source":{"id":"2010.05673","kind":"arxiv","version":2}},"canonical_sha256":"d0bd8b5714ee31eb3ff11620a1489ed500321c5233c0461d5ec6c3d1b6b6e12e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0bd8b5714ee31eb3ff11620a1489ed500321c5233c0461d5ec6c3d1b6b6e12e","first_computed_at":"2026-07-05T01:43:42.626015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:42.626015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p/nPzEBhcLqT4O24NGdm2GSyQWMLd23GFukLHxkWKJC729A5x+6ZKOT6KlGF4QVJEE3w8gv3U0uHULrsK8HlCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:42.626506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.05673","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41272e006e1e897506fb61a8d474fd39c3123b2b693535531704582cbb58a490","sha256:560f5ab2d641a63b3981ef4859b5230abb82b5703083dd1dc44d331d9c70cf59"],"state_sha256":"5082004a4dbac3e0c86b8f65125058e1a0a123006a2b63d7d66e6c1c535f79a6"}