What is she best known for?
The fields of study she is best known for:
- Artificial intelligence
- Machine learning
- Statistics
Her main research concerns Artificial intelligence, Reinforcement learning, Machine learning, Variation and Feature.
The various areas that Doina Precup examines in her Artificial intelligence study include Curiosity and Pattern recognition.
Her work deals with themes such as Information theory, Markov decision process, Algorithm, Randomness and Coding, which intersect with Reinforcement learning.
Her work in the fields of Markov decision process, such as Partially observable Markov decision process, intersects with other areas such as Dirichlet distribution.
Doina Precup has researched Machine learning in several fields, including Reproducibility, Key and Benchmark.
Doina Precup combines subjects such as Representation and Measure with her study of Variation.
Her most cited work include:
- Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control (117 citations)
- An information-theoretic approach to curiosity-driven reinforcement learning (104 citations)
- Classification of Normal and Hypoxic Fetuses From Systems Modeling of Intrapartum Cardiotocography (90 citations)
What are the main themes of her work throughout her whole career to date?
Doina Precup spends much of her time researching Artificial intelligence, Reinforcement learning, Machine learning, Mathematical optimization and Markov decision process.
Her work carried out in the field of Artificial intelligence brings together such families of science as Markov process, State, Computer vision and Pattern recognition.
The concepts of her Pattern recognition study are interwoven with issues in Probabilistic logic and Feature.
Her study looks at the relationship between Reinforcement learning and topics such as Theoretical computer science, which overlap with Graph.
Her Dynamic programming study in the realm of Mathematical optimization interacts with subjects such as Set.
As a part of the same scientific study, Doina Precup usually deals with the Markov decision process, concentrating on Bellman equation and frequently concerns with Q-learning.
She most often published in these fields:
- Artificial intelligence (43.75%)
- Reinforcement learning (31.73%)
- Machine learning (18.27%)
What were the highlights of her more recent work (between 2018-2021)?
- Reinforcement learning (31.73%)
- Artificial intelligence (43.75%)
- Machine learning (18.27%)
In recent papers she was focusing on the following fields of study:
Doina Precup mostly deals with Reinforcement learning, Artificial intelligence, Machine learning, Theoretical computer science and Artificial neural network.
In the subject of general Reinforcement learning, her work in Temporal difference learning is often linked to Variance, thereby combining diverse domains of study.
Her Machine learning research incorporates elements of Segmentation, Sample and Realization.
Her Theoretical computer science research includes themes of Graph, Embedding, Graph, Value and Generalization error.
Her Artificial neural network research incorporates themes from Inference, Training set, Simulation and Affine transformation.
Her Mathematical optimization study combines topics in areas such as Upper and lower bounds and Multi-agent system.
Between 2018 and 2021, her most popular works were:
- Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks (40 citations)
- Invariant Causal Prediction for Block MDPs (15 citations)
- Fast reinforcement learning with generalized policy updates (11 citations)
In her most recent research, the most cited papers focused on:
- Artificial intelligence
- Machine learning
- Statistics
The scientist’s investigation covers issues in Reinforcement learning, Artificial intelligence, Theoretical computer science, Artificial neural network and Leverage.
Her Reinforcement learning study which covers State space that intersects with Invariant.
Her research combines Machine learning and Artificial intelligence.
Doina Precup has included themes like Value, Krylov subspace, Activation function and Graph in her Theoretical computer science study.
As part of the same scientific family, Doina Precup usually focuses on Artificial neural network, concentrating on Robustness and intersecting with Regularization.
Her Leverage research focuses on subjects like Deep learning, which are linked to Decision problem and Linear combination.
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.
