{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:K2YO4UTW2PAQ3NEXX433HIBRAX","short_pith_number":"pith:K2YO4UTW","schema_version":"1.0","canonical_sha256":"56b0ee5276d3c10db497bf37b3a03105f3b3d43eda04f6fbd7dfdc782fb53faf","source":{"kind":"arxiv","id":"2008.07353","version":1},"attestation_state":"computed","paper":{"title":"On the Sample Complexity of Reinforcement Learning with Policy Space Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Wenlong Mou, Xi Chen, Zheng Wen","submitted_at":"2020-08-17T14:26:18Z","abstract_excerpt":"We study the optimal sample complexity in large-scale Reinforcement Learning (RL) problems with policy space generalization, i.e. the agent has a prior knowledge that the optimal policy lies in a known policy space. Existing results show that without a generalization model, the sample complexity of an RL algorithm will inevitably depend on the cardinalities of state space and action space, which are intractably large in many practical problems.\n  To avoid such undesirable dependence on the state and action space sizes, this paper proposes a new notion of eluder dimension for the policy space, "},"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":"2008.07353","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-17T14:26:18Z","cross_cats_sorted":["cs.AI","cs.DS","stat.ML"],"title_canon_sha256":"d8efce708f48de3d2ecd1ae8c305d17e6be31cf405be51bb43011555e2795ea2","abstract_canon_sha256":"444c246d3c957b6fc488ef0d725202eda38484811a95c2212fd7a75102e813f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:38.875882Z","signature_b64":"dXJiW4SXi9R/PluUHlhE+5rCk5A++6aFrT6DAAQcWrG2fx0o1OmiTv25xADhSuPk+oEBjin8eGKpcYboXd9YAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56b0ee5276d3c10db497bf37b3a03105f3b3d43eda04f6fbd7dfdc782fb53faf","last_reissued_at":"2026-07-05T01:27:38.875478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:38.875478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Sample Complexity of Reinforcement Learning with Policy Space Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Wenlong Mou, Xi Chen, Zheng Wen","submitted_at":"2020-08-17T14:26:18Z","abstract_excerpt":"We study the optimal sample complexity in large-scale Reinforcement Learning (RL) problems with policy space generalization, i.e. the agent has a prior knowledge that the optimal policy lies in a known policy space. Existing results show that without a generalization model, the sample complexity of an RL algorithm will inevitably depend on the cardinalities of state space and action space, which are intractably large in many practical problems.\n  To avoid such undesirable dependence on the state and action space sizes, this paper proposes a new notion of eluder dimension for the policy space, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07353","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.07353/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2008.07353","created_at":"2026-07-05T01:27:38.875539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.07353v1","created_at":"2026-07-05T01:27:38.875539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07353","created_at":"2026-07-05T01:27:38.875539+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2YO4UTW2PAQ","created_at":"2026-07-05T01:27:38.875539+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2YO4UTW2PAQ3NEX","created_at":"2026-07-05T01:27:38.875539+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2YO4UTW","created_at":"2026-07-05T01:27:38.875539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.13048","citing_title":"The Space Complexity of Learning-Unlearning Algorithms","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2YO4UTW2PAQ3NEXX433HIBRAX","json":"https://pith.science/pith/K2YO4UTW2PAQ3NEXX433HIBRAX.json","graph_json":"https://pith.science/api/pith-number/K2YO4UTW2PAQ3NEXX433HIBRAX/graph.json","events_json":"https://pith.science/api/pith-number/K2YO4UTW2PAQ3NEXX433HIBRAX/events.json","paper":"https://pith.science/paper/K2YO4UTW"},"agent_actions":{"view_html":"https://pith.science/pith/K2YO4UTW2PAQ3NEXX433HIBRAX","download_json":"https://pith.science/pith/K2YO4UTW2PAQ3NEXX433HIBRAX.json","view_paper":"https://pith.science/paper/K2YO4UTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.07353&json=true","fetch_graph":"https://pith.science/api/pith-number/K2YO4UTW2PAQ3NEXX433HIBRAX/graph.json","fetch_events":"https://pith.science/api/pith-number/K2YO4UTW2PAQ3NEXX433HIBRAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2YO4UTW2PAQ3NEXX433HIBRAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2YO4UTW2PAQ3NEXX433HIBRAX/action/storage_attestation","attest_author":"https://pith.science/pith/K2YO4UTW2PAQ3NEXX433HIBRAX/action/author_attestation","sign_citation":"https://pith.science/pith/K2YO4UTW2PAQ3NEXX433HIBRAX/action/citation_signature","submit_replication":"https://pith.science/pith/K2YO4UTW2PAQ3NEXX433HIBRAX/action/replication_record"}},"created_at":"2026-07-05T01:27:38.875539+00:00","updated_at":"2026-07-05T01:27:38.875539+00:00"}