Methods › Reinforcement Learning › Offline Reinforcement Learning Methods › R2D2
Recurrent Replay Distributed DQN
R2D2
Introduced by Steven Kapturowski et al. in Recurrent Experience Replay in Distributed Reinforcement Learning
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Building on the recent successes of distributed training of RL agents, R2D2 is an RL approach that trains a RNN-based RL agents from distributed prioritized experience replay. Using a single network architecture and fixed set of hyperparameters, Recurrent Replay Distributed DQN quadrupled the previous state of the art on Atari-57, and matches the state of the art on DMLab-30. It was the first agent to exceed human-level performance in 52 of the 57 Atari games.
In Syntology repository known, no verified implementation (declared_code; repositories: 2 listed of 2 in the graph, strongest link: official). The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2205.12467) is about this method is not checked.
From the lookup's note on this name: The same name also belongs to the paper “R2D2: Repeatable and Reliable Detector and Descriptor” (arXiv:1906.06195, 544 citations), which the lookup finds cited far more than the paper this answer is about (21 citations), so this answer may be about a different sense of the name. For arXiv:1906.06195: its page on this site · ask the lookup about it.
Origin paper of this answer, arXiv:2205.12467 (its page on this site · its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 25 · with a code link: 13 · where Syntology ran a sample: 6 (5 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 25 tagged: 5 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 25 of 25, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
The R2D2 Deep Neural Network Series for Scalable Non-Cartesian Magnetic Resonance Imaging 12 Mar 2025 · 0 repositories · arXiv:2503.09559
-
Towards a robust R2D2 paradigm for radio-interferometric imaging: revisiting DNN training and architecture 4 Mar 2025 · 0 repositories · arXiv:2503.02554
-
S-R2D2: a spherical extension of the R2D2 deep neural network series paradigm for wide-field radio-interferometric imaging 3 Mar 2025 · 0 repositories · arXiv:2503.01462
-
R2D2: Remembering, Reflecting and Dynamic Decision Making for Web Agents 21 Jan 2025 · 0 repositories · arXiv:2501.12485
-
A Deep-Based Approach for Multi-Descriptor Feature Extraction: Applications on SAR Image Registration 5 Nov 2024 · 1 repository
-
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs 22 Jul 2024 · 2 repositories · arXiv:2407.15549Syntology official (archive's flag): 4 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified (of 11 harvested samples)
-
Does Refusal Training in LLMs Generalize to the Past Tense? 16 Jul 2024 · 1 repository · arXiv:2407.11969Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Simplifying Deep Temporal Difference Learning 5 Jul 2024 · 1 repository · arXiv:2407.04811Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks 2 Apr 2024 · 1 repository · arXiv:2404.02151Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples)
-
R2D2 image reconstruction with model uncertainty quantification in radio astronomy 26 Mar 2024 · 0 repositories · arXiv:2403.18052
-
Scalable Non-Cartesian Magnetic Resonance Imaging with R2D2 26 Mar 2024 · 0 repositories · arXiv:2403.17905
-
The R2D2 deep neural network series paradigm for fast precision imaging in radio astronomy 8 Mar 2024 · 0 repositories · arXiv:2403.05452
-
CLEANing Cygnus A deep and fast with R2D2 6 Sep 2023 · 0 repositories · arXiv:2309.03291
-
Exploring the Promise and Limits of Real-Time Recurrent Learning 30 May 2023 · 1 repository · arXiv:2305.19044
-
HPointLoc: Point-based Indoor Place Recognition using Synthetic RGB-D Images 30 Dec 2022 · 1 repository · arXiv:2212.14649
-
Meta-Referential Games to Learn Compositional Learning Behaviours 16 Jul 2022 · 1 repository · arXiv:2207.08012
-
R2D2: Robust Data-to-Text with Replacement Detection 25 May 2022 · 1 repository · arXiv:2205.12467
-
CCMB: A Large-scale Chinese Cross-modal Benchmark 8 May 2022 · 1 repository · arXiv:2205.03860Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples)
-
Semantic Exploration from Language Abstractions and Pretrained Representations 8 Apr 2022 · 0 repositories · arXiv:2204.05080
-
Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation 1 Mar 2022 · 2 repositories · arXiv:2203.00281Syntology official: harvested for another paper · 0 ran · 1 unverified (of 1 harvested sample)
-
Retrieval-Augmented Reinforcement Learning 17 Feb 2022 · 0 repositories · arXiv:2202.08417
-
Statistically and Computationally Efficient Linear Meta-representation Learning 1 Dec 2021 · 0 repositories
-
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference 15 Oct 2019 · 2 repositories · arXiv:1910.06591Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)
-
R2D2: Reuse & Reduce via Dynamic Weight Diffusion for Training Efficient NLP Models 25 Sep 2019 · 0 repositories
-
Recurrent Experience Replay in Distributed Reinforcement Learning 1 May 2019 · 3 repositories
Tasks archive 2025-07-28
20 shown of 47 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections