Policy space identification in configurable environments

نویسندگان

چکیده

Abstract We study the problem of identifying policy space available to an agent in a learning process, having access set demonstrations generated by playing optimal considered space. introduce approach based on frequentist statistical testing identify parameters that can control, within larger parametric After presenting two identification rules (combinatorial and simplified), applicable under different assumptions space, we provide probabilistic analysis simplified one case linear policies belonging exponential family. To improve performance our rules, make use recently introduced framework Configurable Markov Decision Processes, exploiting opportunity configuring environment induce reveal which it control. Finally, empirical evaluation, both discrete continuous domains, prove effectiveness rules.

برای دانلود باید عضویت طلایی داشته باشید

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

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A configurable protocol architecture for CORBA environments

This paper describes a flexible architecture for building the protocols required to allow interaction between distributed objects in a CORBA environment. A key feature of the architecture is its ability to select the elements of a protocol stack dynamically at bind-time depending on the properties of the interface being accessed. This permits multiple object-invocation protocols to coexist such...

متن کامل

Configurable Ring Oscillator for FPGA Chip Identification

Hardware security and intellectual property protection have become very important for vendors. Instead of storing identification information in the device, the physical unclonable functions (PUF) are widely used for identification. There are various techniques for PUF implementations. PUFs extract secretes from physical characteristics of integrated circuits. They have the unique property of ge...

متن کامل

Multisectoral Actions for Health: Challenges and Opportunities in Complex Policy Environments

Multisectoral actions for health, defined as actions undertaken by non-health sectors to protect the health of the population, are essential in the context of inter-linkages between three dimensions of sustainable development: economic, social, and environmental. These multisectoral actions can address the social and economic factors that influence the health of a population at the local, natio...

متن کامل

Evolutionary Agent-based Policy Analysis in Dynamic Environments Evolutionary Agent-based Policy Analysis in Dynamic Environments

Evolutionary algorithms (EAs) form a rich class of stochastic search methods that use the Darwinian principles of variation and selection to incrementally improve a set of candidate solutions (Eiben and Smith, 2003; Jong, 2006). Both principles can be implemented from a wide variety of components and operators, many with parameters that need to be tuned if the EA is to perform as intended. Tuni...

متن کامل

Argos - A Configurable Access Control System for Interoperable Environments

The integration of autonomous information systems causes a fundamental problem for security management. How to ensure a consistent authorisation state if several independent software components are involved, each having an access control system of its own? In other words, how to ensure an organisation-wide security policy? Argos has been developed for the CHASSIS1 project, where it serves as an...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Machine Learning

سال: 2021

ISSN: ['0885-6125', '1573-0565']

DOI: https://doi.org/10.1007/s10994-021-06033-3