{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6RLUIZWFAJP2DOR6KNPZDIAT2X","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":"09f4c54539a828d64bd5572d34f1a484d233db132f0f2a65ff2a7abb8a73ea70","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T13:28:11Z","title_canon_sha256":"a3dc8ba52a642581d32be79031b0f91d43587b7ba467be54f066bf1dba5f4da5"},"schema_version":"1.0","source":{"id":"2110.02034","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.02034","created_at":"2026-07-05T04:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2110.02034v2","created_at":"2026-07-05T04:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02034","created_at":"2026-07-05T04:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"6RLUIZWFAJP2","created_at":"2026-07-05T04:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"6RLUIZWFAJP2DOR6","created_at":"2026-07-05T04:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"6RLUIZWF","created_at":"2026-07-05T04:05:35Z"}],"graph_snapshots":[{"event_id":"sha256:9fc5666a0972ced13ea77691acc8ffd607718ffbb607ef7d18407bb93a619aa2","target":"graph","created_at":"2026-07-05T04:05:35Z","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/2110.02034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Randomized ensembled double Q-learning (REDQ) (Chen et al., 2021b) has recently achieved state-of-the-art sample efficiency on continuous-action reinforcement learning benchmarks. This superior sample efficiency is made possible by using a large Q-function ensemble. However, REDQ is much less computationally efficient than non-ensemble counterparts such as Soft Actor-Critic (SAC) (Haarnoja et al., 2018a). To make REDQ more computationally efficient, we propose a method of improving computational efficiency called DroQ, which is a variant of REDQ that uses a small ensemble of dropout Q-function","authors_text":"Taisei Hashimoto, Takahisa Imagawa, Takashi Onishi, Takuya Hiraoka, Yoshimasa Tsuruoka","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T13:28:11Z","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02034","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:af461e3dc7715a0b9a03fb4b7adf71850a4bbd61fb2f1d1ec2c8184d5ac04d61","target":"record","created_at":"2026-07-05T04:05:35Z","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":"09f4c54539a828d64bd5572d34f1a484d233db132f0f2a65ff2a7abb8a73ea70","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-05T13:28:11Z","title_canon_sha256":"a3dc8ba52a642581d32be79031b0f91d43587b7ba467be54f066bf1dba5f4da5"},"schema_version":"1.0","source":{"id":"2110.02034","kind":"arxiv","version":2}},"canonical_sha256":"f4574466c5025fa1ba3e535f91a013d5d3f993144394993f0f225061af60786c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4574466c5025fa1ba3e535f91a013d5d3f993144394993f0f225061af60786c","first_computed_at":"2026-07-05T04:05:35.404774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:35.404774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kualjZ51InHdTbT8kmLSJNZYsm/Ct6dmS557YbWTwr+K9ifFqyxBnaUrmLUbgj3EvrBc6olTPv8YICpe1FofAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:35.405196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.02034","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af461e3dc7715a0b9a03fb4b7adf71850a4bbd61fb2f1d1ec2c8184d5ac04d61","sha256:9fc5666a0972ced13ea77691acc8ffd607718ffbb607ef7d18407bb93a619aa2"],"state_sha256":"35220baa2129d07bbdff1b72dc49356b79ad9267bd6a11c509c51b020c357181"}