What is he best known for?
The fields of study he is best known for:
- Artificial intelligence
- Statistics
- Machine learning
The scientist’s investigation covers issues in Artificial intelligence, Reinforcement learning, Mathematical optimization, Machine learning and Upper and lower bounds.
His study focuses on the intersection of Artificial intelligence and fields such as Active learning with connections in the field of Computational learning theory.
His research in Reinforcement learning intersects with topics in End-to-end principle, Posterior probability, Human–computer interaction and Bellman equation.
His study in Mathematical optimization is interdisciplinary in nature, drawing from both Value, Markov decision process and Applied mathematics.
The Machine learning study combines topics in areas such as Sampling, Bayesian probability and Doubly robust.
His Thompson sampling research incorporates elements of Learning theory and Heuristic.
His most cited work include:
- A contextual-bandit approach to personalized news article recommendation (1439 citations)
- Parallelized Stochastic Gradient Descent (877 citations)
- An Empirical Evaluation of Thompson Sampling (767 citations)
What are the main themes of his work throughout his whole career to date?
His primary areas of study are Artificial intelligence, Reinforcement learning, Machine learning, Mathematical optimization and Markov decision process.
His study on Artificial neural network and Thompson sampling is often connected to Action as part of broader study in Artificial intelligence.
His Reinforcement learning research includes elements of Bellman equation, Stationary distribution, Function approximation and Benchmark.
His study looks at the intersection of Machine learning and topics like Search engine with Ranking.
His studies examine the connections between Mathematical optimization and genetics, as well as such issues in Estimator, with regards to Importance sampling.
His Markov decision process research integrates issues from Algorithm, State and Probably approximately correct learning.
He most often published in these fields:
- Artificial intelligence (45.59%)
- Reinforcement learning (41.67%)
- Machine learning (25.00%)
What were the highlights of his more recent work (between 2019-2021)?
- Reinforcement learning (41.67%)
- Stationary distribution (6.37%)
- Mathematical optimization (21.57%)
In recent papers he was focusing on the following fields of study:
Lihong Li focuses on Reinforcement learning, Stationary distribution, Mathematical optimization, Applied mathematics and Benchmark.
His Reinforcement learning research is multidisciplinary, incorporating perspectives in Markov decision process and Importance sampling.
The concepts of his Mathematical optimization study are interwoven with issues in Estimator, Function space, Generalized estimating equation and Confidence interval.
His research investigates the connection with Applied mathematics and areas like Markov chain which intersect with concerns in Monte Carlo method, Constraint, Divergence and Queueing theory.
His studies in Benchmark integrate themes in fields like Artificial neural network, Posterior probability and Thompson sampling.
Lihong Li is researching Thompson sampling as part of the investigation of Regret and Artificial intelligence.
Between 2019 and 2021, his most popular works were:
- GenDICE: Generalized Offline Estimation of Stationary Values (32 citations)
- Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation (16 citations)
- Off-Policy Evaluation via the Regularized Lagrangian. (12 citations)
In his most recent research, the most cited papers focused on:
- Artificial intelligence
- Statistics
- Machine learning
His primary scientific interests are in Reinforcement learning, Applied mathematics, Stationary distribution, Estimator and Mathematical optimization.
His Reinforcement learning study frequently draws parallels with other fields, such as Importance sampling.
His Importance sampling study combines topics in areas such as Bellman equation and Doubly robust.
His Applied mathematics study incorporates themes from Divergence, Constraint, Markov chain, Benchmark and Monte Carlo method.
His Estimator study integrates concerns from other disciplines, such as Linear programming and Stability.
Mathematical optimization is frequently linked to Black box in his study.
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.
