This program aims to reunite researchers across disciplines that have played a role in developing the theory of reinforcement learning. It will review past developments and identify promising directions of research, with an emphasis on addressing existing open problems, ranging from the design of efficient, scalable algorithms for exploration to how to control learning and planning. It also aims to deepen the understanding of model-free vs. model-based learning and control, and the design of efficient methods to exploit structure and adapt to easier environments.
The program focused on the following four themes:
- Optimization: How and why can deep models be fit to observed (training) data?
- Generalization: Why do these trained models work well on similar but unobserved (test) data?
- Robustness: How can we analyze and improve the performance of these models when applied outside their intended conditions?
- Generative methods: How can deep learning be used to model probability distributions?
The goal of this project is to provide free, high quality, interactive, web-based resources for students and teachers of probability and statistics. Basically, our project consists of an integrated set of components that includes expository text, applets, data sets, biographical sketches, and an object library. Please read the Introduction for more information about the content, structure, mathematical prerequisites, and organization of the project. Technologies and Browser Requirements This site uses a number of advanced (but open and standard) technologies, including the Mathematics Markup Language (MathML), for portable and notationally correct mathematical expressions, and Java for the applets. See the Introduction for more information about the technologies used.
Introduction to Maude: ToC This is the ToC of the Algebraic Specification of Hardware and Software module. The first part contains the Introduction to Maude course; the second (when written) will contain the Microprocessor Verification course. The first (non-technical) section is here (PDF). It outlines the contents of the course. 1. Term Rewriting (PDF) 2. Basic Maude (PDF) 3. Sort Hierarchies and Membership Axioms (PDF) 4. A Microprocessor Example (PDF)
R. Sharipov. (2004)cite arxiv:math/0412421Comment: The textbook, AmSTeX, 132 pages, amsppt style, prepared for double side printing on letter size paper.