What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Machine learning
- Artificial neural network
His primary scientific interests are in Artificial intelligence, Machine learning, Structured prediction, Robot and Mathematical optimization.
Mobile robot, Robotics, Probabilistic logic, Inference and Principle of maximum entropy are the primary areas of interest in his Artificial intelligence study.
When carried out as part of a general Machine learning research project, his work on Markov chain is frequently linked to work in Context, therefore connecting diverse disciplines of study.
His Structured prediction study incorporates themes from Margin, Iterative method, Regret, Supervised learning and Reinforcement learning.
As a member of one scientific family, he mostly works in the field of Robot, focusing on Trajectory and, on occasion, Optimal control and Control engineering.
His Mathematical optimization study integrates concerns from other disciplines, such as Chomp and Control theory.
His most cited work include:
- Reinforcement learning in robotics: A survey (1428 citations)
- Maximum entropy inverse reinforcement learning (1404 citations)
- A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning (1249 citations)
What are the main themes of his work throughout his whole career to date?
J. Andrew Bagnell mainly focuses on Artificial intelligence, Machine learning, Mathematical optimization, Robot and Robotics.
His Artificial intelligence research includes themes of Human–computer interaction and Computer vision.
His research in Machine learning intersects with topics in Reduction, Submodular set function and Probabilistic logic.
His study in Mathematical optimization is interdisciplinary in nature, drawing from both Principle of maximum entropy, Sequence, Computation and Reinforcement learning.
J. Andrew Bagnell has researched Robot in several fields, including Trajectory, Task and Optimal control.
His Robotics study combines topics from a wide range of disciplines, such as Mobile robot navigation, Motion and Robot learning.
He most often published in these fields:
- Artificial intelligence (57.83%)
- Machine learning (28.92%)
- Mathematical optimization (27.11%)
What were the highlights of his more recent work (between 2017-2021)?
- Mathematical optimization (27.11%)
- Reinforcement learning (12.05%)
- Simple (4.82%)
In recent papers he was focusing on the following fields of study:
J. Andrew Bagnell focuses on Mathematical optimization, Reinforcement learning, Simple, Object and Task.
His Mathematical optimization study combines topics in areas such as Artificial neural network and Stationary point.
Reinforcement learning is a subfield of Artificial intelligence that J. Andrew Bagnell investigates.
His Artificial intelligence research includes themes of Machine learning and Metric.
J. Andrew Bagnell focuses mostly in the field of Object, narrowing it down to matters related to Face and, in some cases, Robot.
His biological study spans a wide range of topics, including Motion planning, Mobile robot and Nonlinear system.
Between 2017 and 2021, his most popular works were:
- An Algorithmic Perspective on Imitation Learning (195 citations)
- Shared autonomy via hindsight optimization for teleoperation and teaming (61 citations)
- Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learning (23 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Artificial neural network
J. Andrew Bagnell spends much of his time researching Mathematical optimization, Markov decision process, Reinforcement learning, Function and Horizon.
His studies deal with areas such as Artificial neural network, Sequence and Computation as well as Mathematical optimization.
His studies in Artificial neural network integrate themes in fields like Tree, Control and Optimal control.
His Reinforcement learning study integrates concerns from other disciplines, such as Categorization, Structured prediction, Set, Supervised learning and Natural language.
His work carried out in the field of Function brings together such families of science as Intelligent agent and Human–computer interaction.
Horizon combines with fields such as Time horizon, Imitation learning and Oracle in his work.
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.
