What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Artificial neural network
Martin Riedmiller focuses on Artificial intelligence, Reinforcement learning, Machine learning, Convolutional neural network and Artificial neural network.
Many of his studies on Artificial intelligence apply to Pattern recognition as well.
The various areas that Martin Riedmiller examines in his Reinforcement learning study include Task, Function, Control, Set and Robot.
His Set research includes themes of Variety, Temporal difference learning and Sensory processing.
His Machine learning study deals with Bellman equation intersecting with Learning environment.
His Artificial neural network research is mostly focused on the topic Supervised learning.
His most cited work include:
- Human-level control through deep reinforcement learning (11046 citations)
- Playing Atari with Deep Reinforcement Learning (4302 citations)
- A direct adaptive method for faster backpropagation learning: the RPROP algorithm (3445 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of investigation include Artificial intelligence, Reinforcement learning, Machine learning, Robot and Artificial neural network.
His Artificial intelligence research is multidisciplinary, incorporating perspectives in Task and Computer vision.
His research in Reinforcement learning intersects with topics in Control, Markov decision process, Mathematical optimization and Set.
His Machine learning research is multidisciplinary, incorporating elements of Function and Benchmark.
His work deals with themes such as Range, Simulation and Human–computer interaction, which intersect with Robot.
His study in Artificial neural network is interdisciplinary in nature, drawing from both Intelligent control, Control theory and Bellman equation.
He most often published in these fields:
- Artificial intelligence (68.89%)
- Reinforcement learning (58.89%)
- Machine learning (25.56%)
What were the highlights of his more recent work (between 2017-2021)?
- Reinforcement learning (58.89%)
- Artificial intelligence (68.89%)
- Mathematical optimization (15.00%)
In recent papers he was focusing on the following fields of study:
His primary scientific interests are in Reinforcement learning, Artificial intelligence, Mathematical optimization, Robot and Control.
Martin Riedmiller has researched Reinforcement learning in several fields, including Kullback–Leibler divergence, Set, Human–computer interaction and Hyperparameter.
The Artificial intelligence study combines topics in areas such as Machine learning, Scratch and Task.
His work deals with themes such as Sample and Robustness, which intersect with Mathematical optimization.
As a member of one scientific family, Martin Riedmiller mostly works in the field of Robot, focusing on Inference and, on occasion, Hindsight bias, Backpropagation, Dynamic programming and Embedding.
His Control research is multidisciplinary, incorporating elements of Tree, Computation, Local search and Adaptation.
Between 2017 and 2021, his most popular works were:
- DeepMind Control Suite (258 citations)
- Learning an Embedding Space for Transferable Robot Skills (145 citations)
- Learning by Playing - Solving Sparse Reward Tasks from Scratch (137 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Artificial neural network
The scientist’s investigation covers issues in Reinforcement learning, Artificial intelligence, Inference, Kullback–Leibler divergence and Maximum a posteriori estimation.
His research integrates issues of Programming language and Physics engine in his study of Reinforcement learning.
His studies in Artificial intelligence integrate themes in fields like Scratch and Set.
His research in Set intersects with topics in Latent variable and Parameterized complexity.
His Inference study combines topics in areas such as Graph, Theoretical computer science, Trajectory optimization and System identification.
His Kullback–Leibler divergence research includes elements of Parametric statistics, Mathematical optimization, Premature convergence, Hyperparameter and Robustness.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
