Science Explorer Back to mapMap
Discussion
Topic · Artificial Intelligence

Reinforcement Learning in Robotics

Reinforcement Learning in Robotics is a research topic within Artificial Intelligence. Science Explorer counts 21k research works in it since 1956. 9.8% of them reached the world's top 10% most cited for their field and year.

This cluster of papers encompasses a wide range of advancements in reinforcement learning algorithms and their applications, including deep learning, neural networks, robotics, autonomous control, policy gradient methods, multi-agent systems, model-based learning, curiosity-driven exploration, and simulation to real-world transfer.

  • Reinforcement Learning
  • Deep Learning
  • Neural Networks
  • Robotics
  • Autonomous Control
  • Policy Gradient
  • Multi-Agent Systems
  • Model-Based Learning
  • Curiosity-Driven Exploration
  • Simulation to Real-world Transfer
Research works
21k
fractional, since 1956
In the world top 10%
2k
per year above
Top-10% rate
9.8%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+74%
the tick is no change
Largest producer
China
44% of the 10 largest, 2022-now
Reinforcement Learning in Robotics

Which countries lead Reinforcement Learning in Robotics research?

By volume, China and the United States publish the most (3.1k and 1.6k works in 2022-now).

By volume, 2022-now

  1. 1 China 3.1k works
  2. 2 United States 1.6k works
  3. 3 United Kingdom 377 works
  4. 4 India 355 works
  5. 5 Germany 347 works
  6. 6 Japan 303 works
  7. 7 Canada 222 works
  8. 8 South Korea 217 works
  9. 9 Italy 190 works
  10. 10 France 175 works

How concentrated that is

The same countries as shares of everything the list above accounts for. A node where two countries do two thirds of the work and one spread evenly across twelve read alike as a ranking and not at all alike here.

China: 44.4%United States: 23.8%United Kingdom: 5.5%India: 5.2%6 others listed: 21.1%44%largest
China3,054 · 44.4%United States1,640 · 23.8%United Kingdom377 · 5.5%India355 · 5.2%6 others listed1,454 · 21.1%

Shares of the rows listed above, not of the whole node.

Which institutions lead Reinforcement Learning in Robotics research?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Reinforcement Learning in Robotics research, followed by Tsinghua University and National University of Defense Technology.

By volume, 2022-now

  1. 1 Chinese Academy of SciencesChina 133 works
  2. 2 Tsinghua UniversityChina 109 works
  3. 3 National University of Defense TechnologyChina 91 works
  4. 4 Shanghai Jiao Tong UniversityChina 75 works
  5. 5 Beihang UniversityChina 66 works
  6. 6 Beijing Institute of TechnologyChina 63 works
  7. 7 Northwestern Polytechnical UniversityChina 60 works
  8. 8 Harbin Institute of TechnologyChina 60 works
  9. 9 Centre National de la Recherche ScientifiqueFrance 58 works
  10. 10 Carnegie Mellon UniversityUnited States 56 works

Who are the leading researchers in Reinforcement Learning in Robotics?

The most-cited researchers publishing on Reinforcement Learning in Robotics include Yoshua Bengio, Geoffrey E. Hinton and Karl John Friston.

  1. 1 Yoshua Bengio Canada 476k citations
  2. 2 Geoffrey E. Hinton Canada 454k citations
  3. 3 Karl John Friston United Kingdom 310k citations
  4. 4 Jian Sun 281k citations
  5. 5 Yann LeCun United States 256k citations
  6. 6 Andrew Zisserman United Kingdom 255k citations
  7. 7 Li Fei-Fei United States 225k citations
  8. 8 Kai You Wang China 224k citations
  9. 9 Ilya Sutskever Canada 219k citations
  10. 10 Trevor J. Darrell United States 206k citations

Ranked by citations received across their whole record, among researchers with at least three works on this topic.

What are the most cited papers in Reinforcement Learning in Robotics?

The most cited paper in Reinforcement Learning in Robotics is "Deep learning in neural networks: An overview" (Jürgen Schmidhuber, 2014), with 18,327 citations. Next come "Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions (Short Paper)" (11,361) and "Mastering the game of Go without human knowledge" (9,370).

Most cited papers
#PaperReleasedCitations
1 Deep learning in neural networks: An overview Jürgen Schmidhuber · Neural Networks Open access 13 Oct 2014 18,327
2 Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions (Short Paper) Esper, Khalil, Spieck, Jan, Sixdenier, Pierre-Louis et al. · arXiv (Cornell University) PreprintOpen access 20 Jul 2017 11,361
3 Mastering the game of Go without human knowledge David Lawrence Silver, Julian Schrittwieser, Karen Simonyan et al. · Nature Oct 2017 9,370
4 Q-learning Christopher J. C. H. Watkins, Peter Dayan · Machine Learning Open access May 1992 9,122
5 Reinforcement Learning: A Survey Leslie Pack Kaelbling, Michael L. Littman, Andrew Moore · Journal of Artificial Intelligence Research Open access May 1996 8,975
All 97 most cited papers, with filters and sorting

Where is Reinforcement Learning in Robotics research done?

The largest centres of Reinforcement Learning in Robotics research in 2022-now are Beijing (China), Shanghai (China), Nanjing (China) and Xi'an (China).

Largest cities, 2022-now

  1. 1 BeijingChina 696 works
  2. 2 ShanghaiChina 256 works
  3. 3 NanjingChina 212 works
  4. 4 Xi'anChina 160 works
  5. 5 ChangshaChina 144 works
  6. 6 ShenzhenChina 120 works
  7. 7 GuangzhouChina 119 works
  8. 8 SingaporeSingapore 116 works
  9. 9 TokyoJapan 115 works
  10. 10 LondonUnited Kingdom 108 works
See Reinforcement Learning in Robotics on the map

Where is the best place to study Reinforcement Learning in Robotics?

Among universities, judged by research, Northeastern University, Nanyang Technological University and Tsinghua University score highest, combining excellence, specialisation, size, growth and international reach. Research strength is one signal when choosing where to study; it does not measure teaching.

0%10%20%30%mean 16.95%fractional works in this field (log) →share of work in the world top 10% →Northeastern Univers…Nanyang Technologica…National University …Tsinghua University
above the meannear itbelow it

One dot per university in the first ten of the table below, at the default weights. The upper left is the interesting corner: small places doing unusually strong work.

Excellenceshare of its work in the world top 10%, 2022-now and all time averaged
40%
Specialisationhow much of its work is in this field, counted up to 10× the world share
10%
Sizeits output in this field, on a log scale
30%
Growthoutput growth, counted from -20% to +20%
10%
Internationalshare of its work with a co-author abroad
10%
Each slider sets a weight; the share it gets of the score is beside it.
#UniversityScoreTop 10%SpecialisationWorksGrowth
1Northeastern UniversityChina 80.427.2%7.0×46 +111.2%
2Nanyang Technological UniversitySingapore 75.623.2%7.8×46 +59.6%
3Tsinghua UniversityChina 71.715.9%6.4×109 +77.2%
4National University of SingaporeSingapore 67.119.1%4.5×40 +182.1%
5Beihang UniversityChina 66.815.7%8.1×66 +232.9%
6Massachusetts Institute of TechnologyUnited States 62.816.7%7.6×40 +0.2%
7Shanghai Jiao Tong UniversityChina 61.813.4%3.5×75 +147.5%
8National University of Defense TechnologyChina 61.610.2%16.0×91 +46.6%
9Beijing Institute of TechnologyChina 61.612.7%7.2×63 +189.9%
10Southeast UniversityChina 61.315.4%4.2×45 +203.9%

Universities only. The score blends excellence (40%), size (30%), specialisation (10%), growth (10%), international reach (10%), 2022-now; growth compares 2018-21 with 2022-25 and counts up to +20%, since a jump from a small base is mostly noise.

Every institution in Reinforcement Learning in Robotics, country by country

Is Reinforcement Learning in Robotics research growing?

Output in 2022-2025 was 74% higher than in 2018-2021, peaking in 2025. The fastest-growing topics are Reinforcement Learning in Robotics.

still counting19801990200020102020
grewheldshrank

The same series as a ribbon: one cell per year, darker for more. The line above answers how much; this answers when.

Its share of all research

Growing output can still be a shrinking share: all of science grows. This is Reinforcement Learning in Robotics as a percentage of every work published that year, 0.032% in 2024.

still counting0.020%0.040%0.060%Reinforcement Learning in Robotics0.040% in 202519801990200020102020

Fractional works of Reinforcement Learning in Robotics over all fractional works that year. How the balance of science has shifted.

How much of it reaches the world top 10%

Year by year.

still counting5%10%15%Reinforcement Learning in Robotics9.7% in 2025200020102020

Of each year's works in it, the share that reached the world's 10% most cited for their field and year. A field is the world for its own topics, so there is no other line to hold it against.

Which topics inside it are moving

Growth and decline on one axis around a shared zero. Two lists side by side hide the thing that matters: whether the growth dwarfs the decline, or the other way round.

Questions people ask

Who leads reinforcement learning research in robotics?

By volume in 2022-now, Chinese Academy of Sciences publishes the most Reinforcement Learning in Robotics research, followed by Tsinghua University and National University of Defense Technology. By volume, China and the United States publish the most (3.1k and 1.6k works in 2022-now).

All 1,273 questions in the Question Catalogue

Discussion

Ask a question or share a note about Reinforcement Learning in Robotics. Posts are plain text and can be reported.