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.
Papers archive 2025-07-28
25 shown of 25, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
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 ran 5 of 11 samples · 6 unverified
-
Does Refusal Training in LLMs Generalize to the Past Tense? 16 Jul 2024 · 1 repository · arXiv:2407.11969Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
-
Simplifying Deep Temporal Difference Learning 5 Jul 2024 · 1 repository · arXiv:2407.04811Syntology ran 3 of 3 samples · 0 unverified
-
Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks 2 Apr 2024 · 1 repository · arXiv:2404.02151Syntology ran 8 of 8 samples · 0 unverified
-
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 ran 0 of 9 samples · 9 unverified
-
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 ran 0 of 1 samples · 1 unverified
-
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 ran 0 of 6 samples · 6 unverified
-
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