D4RL

data category: Reinforcement learning environments · 0 papers in the last 7 days

← Most-used data · All Reinforcement learning environments datasets

Simulators and benchmark suites for training and comparing reinforcement learning agents.

Names searched for: D4RL

Key findings#

From Nov 2023 to Oct 2026, 49 archived papers mentioned D4RL in their title, abstract or keywords (the search of earlier months' full texts is still under way), most of them in Sep 2024 (4).
D4RL was mentioned in 1 paper in the last 30 days (2026-10-07 to 2026-11-05), ranking #165 of the 246 datasets mentioned.
By journal category: AI (1).
Most of them appeared in Pattern Recognition (1).
From 2017 to 2026 (so far), D4RL was mentioned in 55 papers in the tracked journals, most of them in AI (54) and operations research (1).
11 of them were published in 2025, against 0 in 2017.
Since 2023, the institutions with the most of these papers were Jilin University (5), National University of Defense Technology (5) and Shenzhen University (4).
The journals publishing most of them were IEEE Transactions on Neural Networks and Learning Systems (13), Machine Learning (7) and Expert Systems with Applications (5).
The most-cited of them is “Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods” (IEEE Transactions on Neural Networks and Learning Systems, 2024), with 176 citations.
Papers use D4RL most often with MuJoCo (18), OpenAI Gym / Gymnasium (8) and StarCraft (7); it has 6 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST.

Mentions over 36 months#

Papers mentioning it by publication month, Nov 2023 to Oct 2026 (titles, abstracts and keywords; the full texts of earlier months are still being searched)
Trend	Nov 23–Oct 24	Nov 24–Oct 25	Nov 25–Oct 26	36 months
	16	10	23	49

Papers per year#

20172026 (so far)

Papers per publication year and category
Category	2022	2023	2024	2025	2026 (so far)
AI	1	9	16	11	17
Operations Research	0	0	0	0	1
All categories	1	9	16	11	18

Where the papers come from#

Journals with the most papers, since 2023
#	Journal	Papers
1	IEEE Transactions on Neural Networks and Learning Systems	13
2	Machine Learning	7
3	Expert Systems with Applications	5
4	Neural Networks	4
5	Neural Computing and Applications	4
6	Pattern Recognition	3
7	IEEE Transactions on Pattern Analysis and Machine Intelligence	3
8	Information Processing & Management	2
9	Applied Intelligence	2
10	Knowledge-Based Systems	2

Institutions with the most papers, since 2023
#	Institution	Papers
1	Jilin University	5
2	National University of Defense Technology	5
3	Shenzhen University	4
4	Hainan University	3
5	Nanjing University	3
6	Northwestern University	3
7	Shanghai Artificial Intelligence Laboratory	3
8	Shanghai Jiao Tong University	3
9	The Alan Turing Institute	3
10	Tsinghua University	3

Countries with the most papers, since 2023
#	Country	Papers
1	China	42
2	United States	9
3	United Kingdom	5
4	Hong Kong	3
5	Australia	2
6	Canada	2
7	Switzerland	2
8	Germany	2
9	Singapore	2
10	Czechia	1

Keywords with the most papers, since 2023
#	Keyword	Papers
1	offline reinforcement learning	36
2	D4RL	17
3	D4RL benchmark	16
4	distribution shift	15
5	out-of-distribution actions	9
6	sample efficiency	8
7	behavior cloning	6
8	offline-to-online reinforcement learning	6
9	reinforcement learning	6
10	convergence analysis	5

Most-cited papers#

Most-cited papers since 2017
#	Citations	Per month	Title	Journal	Published	Authors
1	176	7.5	Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods	IEEE Transactions on Neural Networks and Learning Systems	2024-11-25	Yuji Cao, Huan Qi Zhao, Yuheng Cheng et al.
2	84	3.1	Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms	IEEE Transactions on Evolutionary Computation	2024-08-14	Pengyi Li, Jianye Hao, Hongyao Tang et al.
3	47	1.5	Dynamic datasets and market environments for financial reinforcement learning	Machine Learning	2024-02-26	Xiao-Yang Liu, Ziyi Xia, Hongyang Yang et al.
4	34	0.9	Sample Efficient Offline-to-Online Reinforcement Learning	IEEE Transactions on Knowledge and Data Engineering	2023-08-07	Siyuan Guo, Lixin Zou, Hechang Chen et al.
5	18	0.5	Efficient Offline Reinforcement Learning With Relaxed Conservatism	IEEE Transactions on Pattern Analysis and Machine Intelligence	2024-02-12	Longyang Huang, Botao Dong, Weidong Zhang

Archive counts by publication year: a paper counts when its title, abstract or keywords name the dataset, or when OpenAlex's full-text search finds it there (searched for the last 30 days' papers and, by a pass over the past years, for older ones). Names added to the list later are looked for in older papers as the archive is read again.

Used together with#

Papers use D4RL most often with MuJoCo (18), OpenAI Gym / Gymnasium (8) and StarCraft (7); it has 6 partners in the code and data network, in the group around ImageNet, CIFAR-10 / CIFAR-100, MNIST / Fashion-MNIST. The whole network →

What papers use D4RL together with (at least 3 papers; lift 1 = chance)
Used with	Type	Papers using both	Lift
MuJoCo	Dataset	18	104.4
OpenAI Gym / Gymnasium	Dataset	8	56.1
StarCraft	Dataset	7	42.9
Atari (Arcade Learning Environment)	Dataset	5	34.0
DeepMind Control Suite	Dataset	4	108.7
ImageNet	Dataset	3	1.1

Papers mentioning D4RL in the last 30 days, newest first.
Date	Title	Journal	Authors	Affiliations
2026-10-22	Mitigating state–action distribution shifts in offline reinforcement learning via implicit state–state planning	Pattern Recognition	Shuo Cao, Yuhu Cheng, Xuesong Wang	China University of Mining and Technology

Cite this page

Scholar4AI. (2026). D4RL. Journal and Conference Research Rankings. Retrieved November 5, 2026, from https://scholar4ai.com/datasets/d4rl

@misc{scholar4ai-datasets-d4rl,
  author = {{Scholar4AI}},
  title = {D4RL},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/datasets/d4rl}},
  urldate = {2026-11-05},
  note = {Journal and Conference Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}

Free to reuse for non-commercial purposes with attribution (CC BY-NC 4.0).