{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/r2d2","slug":"r2d2","name":"R2D2","full_name":"Recurrent Replay Distributed DQN","full_name_withheld":false,"description_markdown":"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. \r\nUsing 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. \r\nIt was the first agent to exceed human-level performance in 52 of the 57 Atari games.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Recurrent Experience Replay in Distributed Reinforcement Learning","paper":"/paper/recurrent-experience-replay-in-distributed","first_author":"Steven Kapturowski","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/recurrent-experience-replay-in-distributed"},"source":{"url":"https://openreview.net/forum?id=r1lyTjAqYX","title":"Recurrent Experience Replay in Distributed Reinforcement Learning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"Offline Reinforcement Learning Methods","url":"/methods/category/offline-reinforcement-learning-methods","pwc_aliases":[]}],"n_papers_tagged":25,"archive_num_papers":25,"papers_newest_first":[{"paper":null,"slug":"the-r2d2-deep-neural-network-series-for","title":"The R2D2 Deep Neural Network Series for Scalable Non-Cartesian Magnetic Resonance Imaging","date":"2025-03-12","arxiv_id":"2503.09559","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-robust-r2d2-paradigm-for-radio","title":"Towards a robust R2D2 paradigm for radio-interferometric imaging: revisiting DNN training and architecture","date":"2025-03-04","arxiv_id":"2503.02554","n_code_links":0,"syntology":null},{"paper":null,"slug":"s-r2d2-a-spherical-extension-of-the-r2d2-deep","title":"S-R2D2: a spherical extension of the R2D2 deep neural network series paradigm for wide-field radio-interferometric imaging","date":"2025-03-03","arxiv_id":"2503.01462","n_code_links":0,"syntology":null},{"paper":null,"slug":"r2d2-remembering-reflecting-and-dynamic","title":"R2D2: Remembering, Reflecting and Dynamic Decision Making for Web Agents","date":"2025-01-21","arxiv_id":"2501.12485","n_code_links":0,"syntology":null},{"paper":"/paper/a-deep-based-approach-for-multi-descriptor","slug":"a-deep-based-approach-for-multi-descriptor","title":"A Deep-Based Approach for Multi-Descriptor Feature Extraction: Applications on SAR Image Registration","date":"2024-11-05","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/targeted-latent-adversarial-training-improves","slug":"targeted-latent-adversarial-training-improves","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","date":"2024-07-22","arxiv_id":"2407.15549","n_code_links":2,"syntology":{"ran":5,"of":11,"n_ran_checked":2,"n_instrument":3,"unverified":6,"pointer_only":0,"phrase":"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","official":{"repos":["aengusl/latent-adversarial-training"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/does-refusal-training-in-llms-generalize-to","slug":"does-refusal-training-in-llms-generalize-to","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","date":"2024-07-16","arxiv_id":"2407.11969","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"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","official":{"repos":["tml-epfl/llm-past-tense"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/simplifying-deep-temporal-difference-learning","slug":"simplifying-deep-temporal-difference-learning","title":"Simplifying Deep Temporal Difference Learning","date":"2024-07-05","arxiv_id":"2407.04811","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"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","official":{"repos":["mttga/purejaxql"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/jailbreaking-leading-safety-aligned-llms-with","slug":"jailbreaking-leading-safety-aligned-llms-with","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","date":"2024-04-02","arxiv_id":"2404.02151","n_code_links":1,"syntology":{"ran":8,"of":8,"n_ran_checked":6,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"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","official":{"repos":["tml-epfl/llm-adaptive-attacks"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"r2d2-image-reconstruction-with-model","title":"R2D2 image reconstruction with model uncertainty quantification in radio astronomy","date":"2024-03-26","arxiv_id":"2403.18052","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalable-non-cartesian-magnetic-resonance","title":"Scalable Non-Cartesian Magnetic Resonance Imaging with R2D2","date":"2024-03-26","arxiv_id":"2403.17905","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-r2d2-deep-neural-network-series-paradigm","title":"The R2D2 deep neural network series paradigm for fast precision imaging in radio astronomy","date":"2024-03-08","arxiv_id":"2403.05452","n_code_links":0,"syntology":null},{"paper":null,"slug":"r2d2-deep-neural-network-series-for-near-real","title":"CLEANing Cygnus A deep and fast with R2D2","date":"2023-09-06","arxiv_id":"2309.03291","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-promise-and-limits-of-real-time","slug":"exploring-the-promise-and-limits-of-real-time","title":"Exploring the Promise and Limits of Real-Time Recurrent Learning","date":"2023-05-30","arxiv_id":"2305.19044","n_code_links":1,"syntology":null},{"paper":"/paper/hpointloc-point-based-indoor-place","slug":"hpointloc-point-based-indoor-place","title":"HPointLoc: Point-based Indoor Place Recognition using Synthetic RGB-D Images","date":"2022-12-30","arxiv_id":"2212.14649","n_code_links":1,"syntology":null},{"paper":"/paper/meta-referential-games-to-learn-compositional-1","slug":"meta-referential-games-to-learn-compositional-1","title":"Meta-Referential Games to Learn Compositional Learning Behaviours","date":"2022-07-16","arxiv_id":"2207.08012","n_code_links":1,"syntology":null},{"paper":"/paper/r2d2-robust-data-to-text-with-replacement","slug":"r2d2-robust-data-to-text-with-replacement","title":"R2D2: Robust Data-to-Text with Replacement Detection","date":"2022-05-25","arxiv_id":"2205.12467","n_code_links":1,"syntology":null},{"paper":"/paper/zero-and-r2d2-a-large-scale-chinese-cross","slug":"zero-and-r2d2-a-large-scale-chinese-cross","title":"CCMB: A Large-scale Chinese Cross-modal Benchmark","date":"2022-05-08","arxiv_id":"2205.03860","n_code_links":1,"syntology":{"ran":8,"of":9,"n_ran_checked":8,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"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","official":{"repos":["yuxie11/R2D2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"semantic-exploration-from-language","title":"Semantic Exploration from Language Abstractions and Pretrained Representations","date":"2022-04-08","arxiv_id":"2204.05080","n_code_links":0,"syntology":null},{"paper":"/paper/fast-r2d2-a-pretrained-recursive-neural","slug":"fast-r2d2-a-pretrained-recursive-neural","title":"Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation","date":"2022-03-01","arxiv_id":"2203.00281","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":{"repos":["alipay/StructuredLM_RTDT"],"state":"official: harvested for another paper","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":null,"slug":"retrieval-augmented-reinforcement-learning-1","title":"Retrieval-Augmented Reinforcement Learning","date":"2022-02-17","arxiv_id":"2202.08417","n_code_links":0,"syntology":null},{"paper":null,"slug":"statistically-and-computationally-efficient-2","title":"Statistically and Computationally Efficient Linear Meta-representation Learning","date":"2021-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/seed-rl-scalable-and-efficient-deep-rl-with-1","slug":"seed-rl-scalable-and-efficient-deep-rl-with-1","title":"SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference","date":"2019-10-15","arxiv_id":"1910.06591","n_code_links":2,"syntology":{"ran":6,"of":6,"n_ran_checked":6,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"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","official":{"repos":["google-research/seed_rl"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"r2d2-reuse-reduce-via-dynamic-weight","title":"R2D2: Reuse & Reduce via Dynamic Weight Diffusion for Training Efficient NLP Models","date":"2019-09-25","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/recurrent-experience-replay-in-distributed","slug":"recurrent-experience-replay-in-distributed","title":"Recurrent Experience Replay in Distributed Reinforcement Learning","date":"2019-05-01","arxiv_id":null,"n_code_links":3,"syntology":null}],"papers_shown":25,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":25,"with_a_code_link":13,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":25,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":1,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":6,"papers_where_code_ran_first_page":"/method/r2d2/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/r2d2/papers/ran/1","json":"/method/r2d2/papers/ran/1.json","rows":6}],"tasks":[{"task":"/task/image-reconstruction","name":"Image Reconstruction","papers":5},{"task":"/task/astronomy","name":"Astronomy","papers":4},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":4},{"task":"/task/retrieval","name":"Retrieval","papers":4},{"task":"/task/radio-interferometry","name":"Radio Interferometry","papers":3},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":3},{"task":"/task/image-retrieval","name":"Image Retrieval","papers":2},{"task":"/task/q-learning","name":"Q-Learning","papers":2},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":2},{"task":"/task/atari-games","name":"Atari Games","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/constituency-grammar-induction","name":"Constituency Grammar Induction","papers":1},{"task":"/task/data-to-text-generation","name":"Data-to-Text Generation","papers":1},{"task":"/task/decision-making","name":"Decision Making","papers":1},{"task":"/task/deep-reinforcement-learning","name":"Deep Reinforcement Learning","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/diagnostic","name":"Diagnostic","papers":1},{"task":"/task/entity-retrieval","name":"Entity Retrieval","papers":1},{"task":"/task/few-shot-learning","name":"Few-Shot Learning","papers":1},{"task":"/task/image-captioning","name":"Image Captioning","papers":1}],"tasks_shown":20,"n_tasks":47,"usage_by_year":[{"year":"2019","papers":3},{"year":"2021","papers":1},{"year":"2022","papers":7},{"year":"2023","papers":2},{"year":"2024","papers":8},{"year":"2025","papers":4}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/r2d2"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=R2D2","read_at":"2026-10-05T01:00:51+00:00","query":"R2D2","kind":"method","have":"declared_code","tier":"repo_known","verified_implementation":false,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"method":"R2D2","origin_arxiv_id":"2205.12467"},"resolution":"exact","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"unknown","archive_paper_arxiv_id":null,"repositories":{"listed":2,"in_graph":2,"list_truncated":false,"strongest_link":"official"},"retrieve_with":null,"name_competition":{"verdict":"outranked","may_be_wrong_sense":true,"bearers_found":6,"served":{"arxiv_id":"2205.12467","citations":21},"leading_other_bearer":{"arxiv_id":"1906.06195","title":"R2D2: Repeatable and Reliable Detector and Descriptor","citations":544,"named_by":["title_prefix"],"bearer_name":"R2D2: Repeatable and Reliable Detector and Descriptor","ask_with":"have('1906.06195')"},"n_other_bearers_listed":5,"note":"'R2D2' is ALSO the name of the paper 'R2D2: Repeatable and Reliable Detector and Descriptor' (arXiv:1906.06195, 544 citations), which is cited FAR more than the paper this answer is about (21). This answer may be about the wrong R2D2. If you meant the better-known one, ask again with that entry of `also_named`."},"name_competition_text":"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.","near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2205.12467","page":"/paper/r2d2-robust-data-to-text-with-replacement","syntology_url":"https://syntology.ai/paper/2205.12467","in_graph_layer":false,"samples":0},"line":"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.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"95e9469e41ee519e8434bac53c591ecad5c819be3f4bc7cfecacd0a31df64cde","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}