{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YOGCNHQBK3Y7JNH2WN4LLP2ACK","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":"122ccf4661d5a773ff62987e60c4c9041808f338b7bb58d031103fcb10c6e7f6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-17T14:48:52Z","title_canon_sha256":"43c4fa06d0dc4dd0406e3631aeda074872e381b29cb490be3350a5853c9b8260"},"schema_version":"1.0","source":{"id":"2111.09159","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.09159","created_at":"2026-07-05T05:16:49Z"},{"alias_kind":"arxiv_version","alias_value":"2111.09159v3","created_at":"2026-07-05T05:16:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.09159","created_at":"2026-07-05T05:16:49Z"},{"alias_kind":"pith_short_12","alias_value":"YOGCNHQBK3Y7","created_at":"2026-07-05T05:16:49Z"},{"alias_kind":"pith_short_16","alias_value":"YOGCNHQBK3Y7JNH2","created_at":"2026-07-05T05:16:49Z"},{"alias_kind":"pith_short_8","alias_value":"YOGCNHQB","created_at":"2026-07-05T05:16:49Z"}],"graph_snapshots":[{"event_id":"sha256:c8fba33da01f63c5c0c29c301d749dac2e0e7866be6a3828d095934e54511137","target":"graph","created_at":"2026-07-05T05:16:49Z","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/2111.09159/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in model-free deep reinforcement learning (DRL) show that simple model-free methods can be highly effective in challenging high-dimensional continuous control tasks. In particular, Truncated Quantile Critics (TQC) achieves state-of-the-art asymptotic training performance on the MuJoCo benchmark with a distributional representation of critics; and Randomized Ensemble Double Q-Learning (REDQ) achieves high sample efficiency that is competitive with state-of-the-art model-based methods using a high update-to-data ratio and target randomization. In this paper, we propose a novel mo","authors_text":"Che Wang, Keith W. Ross, Xinyue Chen, Yanqiu Wu, Yiming Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-17T14:48:52Z","title":"Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.09159","kind":"arxiv","version":3},"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:d52b998267a057b029f6e3fee07deffd7d5f5b7b12cc4f8189ba7c9a77b45c8f","target":"record","created_at":"2026-07-05T05:16:49Z","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":"122ccf4661d5a773ff62987e60c4c9041808f338b7bb58d031103fcb10c6e7f6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-17T14:48:52Z","title_canon_sha256":"43c4fa06d0dc4dd0406e3631aeda074872e381b29cb490be3350a5853c9b8260"},"schema_version":"1.0","source":{"id":"2111.09159","kind":"arxiv","version":3}},"canonical_sha256":"c38c269e0156f1f4b4fab378b5bf4012b34c365d2686ffdc38bb3b81c4025ba9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c38c269e0156f1f4b4fab378b5bf4012b34c365d2686ffdc38bb3b81c4025ba9","first_computed_at":"2026-07-05T05:16:49.655388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:16:49.655388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s4dKveANIjZkNwLPUPUa49CvIGILL2b7w/o5qpfuRw6yeyycz0i010z01QanpP3jJe8x4VkbXyQg5RY/86+9CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:16:49.655815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.09159","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d52b998267a057b029f6e3fee07deffd7d5f5b7b12cc4f8189ba7c9a77b45c8f","sha256:c8fba33da01f63c5c0c29c301d749dac2e0e7866be6a3828d095934e54511137"],"state_sha256":"9c27efc73c2b319b0c8ab490205d9a5a3ad15aded0c03a94584b1489927c6eb8"}