Reinforcement Learning (RL) is the study of agents that learn optimal
behavior by interacting with and receiving rewards and punishments from an unknown
environment. RL agents typically do this by learning value functions that
assign a value to each state (situation) or to each state-action pair. Recently,
there has been...
This thesis addresses the problem of learning dynamic Bayesian network (DBN) models to support reinforcement learning. It focuses on learning regression tree models of the conditional probability distributions of the DBNs. Existing algorithms presume that the stochasticity in the domain can be modeled as a deterministic function with additive noise....
The thesis focuses on model-based approximation methods for reinforcement
learning with large scale applications such as combinatorial optimization problems.
First, the thesis proposes two new model-based methods to stablize the
value–function approximation for reinforcement learning. The first one is the
BFBP algorithm, a batch-like reinforcement learning process which iterates between...
Sequential supervised learning problems arise in many real applications. This dissertation focuses on two important research directions in sequential supervised learning: efficient training and feature induction.
In the direction of efficient training, we study the training of conditional random fields (CRFs), which provide a flexible and powerful model for sequential...
Multi-instance data, in which each object (e.g., a document) is a collection of instances
(e.g., word), are widespread in machine learning, signal processing, computer vision,
bioinformatic, music, and social sciences. Existing probabilistic models, e.g., latent
Dirichlet allocation (LDA), probabilistic latent semantic indexing (pLSI), and discrete
component analysis (DCA), have been...
Many important application problems in engineering can be formalized as nonlinear
optimization tasks. However, numerical methods for solving such problems
are brittle and do not scale well. For example, these methods depend critically
on choosing a good starting point from which to perform the optimization search.
In high-dimensional spaces, numerical...
Easy-first, a search-based structured prediction approach, has been applied to many NLP tasks including dependency parsing and coreference resolution. This approach employs a learned greedy policy (action scoring function) to make easy decisions first, which constrains the remaining decisions and makes them easier. This thesis studies the problem of learning...
Many problems in ecology and conservation biology can be formulated and solved using machine learning algorithms for multi-label classification. This dissertation addresses three topics related to predicting the distributions of multiple species. It improves existing methods and proposes a new modeling paradigm to address the multi-species, multi-label problem. The first...
Knowledge workers are struggling in the information flood. There is a growing interest in intelligent desktop environments that help knowledge workers organize their daily life. Intelligent desktop environments allow the desktop user to define a set of “activities” that characterize the user’s desktop work. These environments then attempt to identify...
In its simplest form, the process of diagnosis is a decision-making process in which the diagnostician performs a sequence of tests culminating in a diagnostic decision. For example, a physician might perform a series of simple measurements (body tem- perature, weight, etc.) and laboratory measurements (white blood count, CT scan,...