Science Explorer Back to mapMap
Discussion
Topic · Computational Theory and Mathematics

Adaptive Dynamic Programming Control

Adaptive Dynamic Programming Control is a research topic within Computational Theory and Mathematics. Science Explorer counts 8k research works in it since 1965. 9.9% of them reached the world's top 10% most cited for their field and year.

This cluster of papers focuses on the application of Adaptive Dynamic Programming and Reinforcement Learning techniques to solve optimal control problems in continuous-time nonlinear systems. It explores the use of neural networks, policy iteration, actor-critic algorithms, and $H_{infty}$ control for online learning and feedback control in various domains such as robotics, energy management, and multi-agent systems.

  • Adaptive Dynamic Programming
  • Reinforcement Learning
  • Optimal Control
  • Neural Networks
  • Continuous-Time Systems
  • Nonlinear Systems
  • Policy Iteration
  • Actor-Critic Algorithm
  • $H_{infty}$ Control
  • Online Learning
Research works
8k
fractional, since 1965
In the world top 10%
788
per year above
Top-10% rate
9.9%
share of its works in the world top 10%
Growth, 2018-21 → 2022-25
+76%
the tick is no change
Largest producer
China
78% of the 10 largest, 2022-now
Adaptive Dynamic Programming Control

Which countries lead Adaptive Dynamic Programming Control research?

By volume, China and the United States publish the most (2.7k and 299 works in 2022-now).

By volume, 2022-now

  1. 1 China 2.7k works
  2. 2 United States 299 works
  3. 3 India 96 works
  4. 4 South Korea 66 works
  5. 5 Iran 66 works
  6. 6 United Kingdom 61 works
  7. 7 Canada 52 works
  8. 8 ?? 51 works
  9. 9 Japan 45 works
  10. 10 Germany 42 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: 77.6%United States: 8.6%India: 2.8%South Korea: 1.9%6 others listed: 9.1%78%largest
China2,687 · 77.6%United States299 · 8.6%India96 · 2.8%South Korea66 · 1.9%6 others listed317 · 9.1%

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

Which institutions lead Adaptive Dynamic Programming Control research?

By volume in 2022-now, Northeastern University publishes the most Adaptive Dynamic Programming Control research, followed by Nanjing University of Aeronautics and Astronautics and Beihang University.

By volume, 2022-now

  1. 1 Northeastern UniversityChina 107 works
  2. 2 Nanjing University of Aeronautics and AstronauticsChina 69 works
  3. 3 Beihang UniversityChina 67 works
  4. 4 Harbin Institute of TechnologyChina 64 works
  5. 5 Northwestern Polytechnical UniversityChina 61 works
  6. 6 Southeast UniversityChina 54 works
  7. 7 Chinese Academy of SciencesChina 50 works
  8. 8 Beijing University of TechnologyChina 48 works
  9. 9 Nanjing University of Science and TechnologyChina 48 works
  10. 10 Bohai UniversityChina 47 works

Who are the leading researchers in Adaptive Dynamic Programming Control?

The most-cited researchers publishing on Adaptive Dynamic Programming Control include Yoshua Bengio, Kai You Wang and Frede Blaabjerg.

  1. 1 Yoshua Bengio Canada 476k citations
  2. 2 Kai You Wang China 224k citations
  3. 3 Frede Blaabjerg Denmark 203k citations
  4. 4 Jürgen Schmidhuber Switzerland 188k citations
  5. 5 Michael I. Jordan United States 182k citations
  6. 6 David Lawrence Silver United Kingdom 168k citations
  7. 7 Han Zhang China 161k citations
  8. 8 Bernhard Schölkopf Germany 148k citations
  9. 9 Tasawar Hayat Pakistan 135k citations
  10. 10 Andrew Y. Ng United States 131k 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 Adaptive Dynamic Programming Control?

The most cited paper in Adaptive Dynamic Programming Control is "Continuous control with deep reinforcement learning" (Timothy Lillicrap, Jonathan J. Hunt, Alexander Pritzel et al., 2015), with 5,364 citations. Next come "Policy Gradient Methods for Reinforcement Learning with Function Approximation" (4,956) and "Robust Adaptive Control of Feedback Linearizable MIMO Nonlinear Systems With Prescribed Performance" (2,762).

Most cited papers
#PaperReleasedCitations
1 Continuous control with deep reinforcement learning Timothy Lillicrap, Jonathan J. Hunt, Alexander Pritzel et al. · arXiv (Cornell University) PreprintOpen access 9 Sep 2015 5,364
2 Policy Gradient Methods for Reinforcement Learning with Function Approximation Richard S. Sutton, David McAllester, Satinder Pal Singh et al. 29 Nov 1999 4,956
3 Robust Adaptive Control of Feedback Linearizable MIMO Nonlinear Systems With Prescribed Performance Charalampos P. Bechlioulis, George A. Rovithakis · IEEE Transactions on Automatic Control Oct 2008 2,762
4 Sigmoid-weighted linear units for neural network function approximation in reinforcement learning Stefan Elfwing, Eiji Uchibe, Kenji Doya · Neural Networks Open access 11 Jan 2018 2,075
5 Systematic design of adaptive controllers for feedback linearizable systems I. Kanellakopoulos, P.V. Kokotović, A. Stephen Morse · IEEE Transactions on Automatic Control Nov 1991 1,962
All 100 most cited papers, with filters and sorting

Where is Adaptive Dynamic Programming Control research done?

The largest centres of Adaptive Dynamic Programming Control research in 2022-now are Beijing (China), Nanjing (China), Shanghai (China) and Xi'an (China). Among places with at least 20 works in it, it is an unusually large share of all research in Jinzhou, Anshan and Qufu.

Largest cities, 2022-now

  1. 1 BeijingChina 412 works
  2. 2 NanjingChina 248 works
  3. 3 ShanghaiChina 139 works
  4. 4 Xi'anChina 139 works
  5. 5 ShenyangChina 117 works
  6. 6 GuangzhouChina 111 works
  7. 7 HarbinChina 103 works
  8. 8 QingdaoChina 87 works
  9. 9 JinzhouChina 86 works
  10. 10 JinanChina 76 works

Where it is the local speciality

  1. JinzhouCN · 86.3 works91×
  2. AnshanCN · 21.9 works35×
  3. QufuCN · 21.3 works29×
  4. QinhuangdaoCN · 25.4 works16×
← less than its size predicts1×more →

Location quotient: how much more of its research is in Adaptive Dynamic Programming Control than the world average.

See Adaptive Dynamic Programming Control on the map

Where is the best place to study Adaptive Dynamic Programming Control?

Among universities, judged by research, Northeastern University, Bohai University and Harbin Institute of Technology 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%20%40%mean 16.95%fractional works in this field (log) →share of work in the world top 10% →Dalian UniversityBohai UniversityNortheastern Univers…Harbin Institute of …
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 65.617.4%35.7×107 +22.2%
2Bohai UniversityChina 65.128.0%137.3×47 +115.5%
3Harbin Institute of TechnologyChina 57.212.3%11.7×64 +73.5%
4Dalian UniversityChina 56.844.7%10.5×8 -
5Beihang UniversityChina 53.79.9%18.1×67 +144.0%
6Beijing University of TechnologyChina 53.313.7%20.7×48 +374.5%
7Liaoning University of TechnologyChina 53.315.4%164.1×40 +6.4%
8Nanjing University of Aeronautics and AstronauticsChina 53.09.0%23.3×69 +61.5%
9Northwestern Polytechnical UniversityChina 53.09.5%15.9×61 +41.1%
10Southeast UniversityChina 52.79.6%11.0×54 +74.3%

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 Adaptive Dynamic Programming Control, country by country

Is Adaptive Dynamic Programming Control research growing?

Output in 2022-2025 was 76% higher than in 2018-2021, peaking in 2025. The fastest-growing topics are Adaptive Dynamic Programming Control.

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 Adaptive Dynamic Programming Control as a percentage of every work published that year, 0.012% in 2024.

still counting0.010%0.020%Adaptive Dynamic Programming Control0.018% in 202519801990200020102020

Fractional works of Adaptive Dynamic Programming Control 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%Adaptive Dynamic Programming Control9.6% 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.

Discussion

Ask a question or share a note about Adaptive Dynamic Programming Control. Posts are plain text and can be reported.