{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WYLLQ42RUU6MX2WMBQPAD6HYBM","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":"8ae42db02e7d4cb9e35344b010fc4c7873ab8f6945f1db1d5f89c32f0dfab988","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T23:17:26Z","title_canon_sha256":"9ea7b8a6ba08dcd2666be68ab9c4d94fe63b1cff28bc2986123f6c277ef90099"},"schema_version":"1.0","source":{"id":"2301.12579","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.12579","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"arxiv_version","alias_value":"2301.12579v2","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12579","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"pith_short_12","alias_value":"WYLLQ42RUU6M","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"pith_short_16","alias_value":"WYLLQ42RUU6MX2WM","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"pith_short_8","alias_value":"WYLLQ42R","created_at":"2026-07-05T06:26:45Z"}],"graph_snapshots":[{"event_id":"sha256:b4b55e7455ee3922a46f4f87a5f81f929ea76ab600f520b6880f2dfbd87c2742","target":"graph","created_at":"2026-07-05T06:26:45Z","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/2301.12579/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The focus of this work is sample-efficient deep reinforcement learning (RL) with a simulator. One useful property of simulators is that it is typically easy to reset the environment to a previously observed state. We propose an algorithmic framework, named uncertainty-first local planning (UFLP), that takes advantage of this property. Concretely, in each data collection iteration, with some probability, our meta-algorithm resets the environment to an observed state which has high uncertainty, instead of sampling according to the initial-state distribution. The agent-environment interaction the","authors_text":"Botao Hao, Csaba Szepesvari, Dong Yin, Nevena Lazic, Nived Rajaraman, Sridhar Thiagarajan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T23:17:26Z","title":"Sample Efficient Deep Reinforcement Learning via Local Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12579","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":"sha256:91734387c0685263bb0e2cb786c621947db22950e250aab76f0f13e034e08385","target":"record","created_at":"2026-07-05T06:26:45Z","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":"8ae42db02e7d4cb9e35344b010fc4c7873ab8f6945f1db1d5f89c32f0dfab988","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T23:17:26Z","title_canon_sha256":"9ea7b8a6ba08dcd2666be68ab9c4d94fe63b1cff28bc2986123f6c277ef90099"},"schema_version":"1.0","source":{"id":"2301.12579","kind":"arxiv","version":2}},"canonical_sha256":"b616b87351a53ccbeacc0c1e01f8f80b3597f79492c02b7a62cb2e23abb2b772","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b616b87351a53ccbeacc0c1e01f8f80b3597f79492c02b7a62cb2e23abb2b772","first_computed_at":"2026-07-05T06:26:45.378982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:45.378982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LD5a1E0SoNk4CZ2GMnW8snh9OIny5MG3c0s4XQSuXqmZLX5E+iVZOWqZUK49yCFiouc8CHDInJ2qQw14xhofAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:45.379550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.12579","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:91734387c0685263bb0e2cb786c621947db22950e250aab76f0f13e034e08385","sha256:b4b55e7455ee3922a46f4f87a5f81f929ea76ab600f520b6880f2dfbd87c2742"],"state_sha256":"9693a45a3087c9e1a583d05e520c3f8c7473b804d81a84c8c4c9608c32b30e40"}