Database Exploration and Bellman

نویسندگان

Theodore Johnson

Amit Marathe

Tamraparni Dasu

چکیده

Large industrial-scale databases tend to be poorly structured, dirty, and very confusing. There are many reasons for this disorder, not the least of which is that the application domains themselves are poorly structured, dirty and confusing. As data analysts, we are often called upon to mine, clean, or otherwise analyze these databases. In this article, we describe the types of problems we have encountered, tools and techniques we have developed to address these problems, and directions for future work.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Contextual Decision Processes with low Bellman rank are PAC-Learnable

This paper studies systematic exploration for reinforcement learning with rich observations and function approximation. We introduce a new model called contextual decision processes, that unifies and generalizes most prior settings. Our first contribution is a complexity measure, the Bellman rank , that we show enables tractable learning of near-optimal behavior in these processes and is natura...

متن کامل

The Uncertainty Bellman Equation and Exploration

We consider the exploration/exploitation problem in reinforcement learning. For exploitation, it is well known that the Bellman equation connects the value at any time-step to the expected value at subsequent time-steps. In this paper we consider a similar uncertainty Bellman equation (UBE), which connects the uncertainty at any time-step to the expected uncertainties at subsequent time-steps, ...

متن کامل

Improving PAC Exploration Using the Median Of Means

We present the first application of the median of means in a PAC exploration algorithm for MDPs. Using the median of means allows us to significantly reduce the dependence of our bounds on the range of values that the value function can take, while introducing a dependence on the (potentially much smaller) variance of the Bellman operator. Additionally, our algorithm is the first algorithm with...

متن کامل

Optimal exploration as a symmetry breaking phenomenon

We study the problem of joint estimation and control for a small example for which we can numerically compute the exact solution. We demonstrate, that optimal exploration is achieved through symmetry breaking in the Bellman equation; that optimal actions can be discontinuous in the beliefs; and that the optimal value function is typically non-differentiable. This could pose a challenge for the ...

متن کامل