Reinforcement Learning by Policy Search

One objective of artificial intelligence is to model the behavior of an intelligent agent interacting with its environment. The environment's transformations can be modeled as a Markov chain, whose state is partially observable to the agent and affected by its actions; such processes are known as partially observable Markov decision processes (POMDPs). While the environment's dynamics are assumed to obey certain rules, the agent does not know them and must learn. In this dissertation we focus on the agent's adaptation as captured by the reinforcement learning framework. This means learning a policy---a mapping of observations into actions---based on feedback from the environment. The learning can be viewed as browsing a set of policies while evaluating them by trial through interaction with the environment. The set of policies is constrained by the architecture of the agent's controller. POMDPs require a controller to have a memory. We investigate controllers with memory, including controllers with external memory, finite state controllers and distributed controllers for multi-agent systems. For these various controllers we work out the details of the algorithms which learn by ascending the gradient of expected cumulative reinforcement. Building on statistical learning theory and experiment design theory, a policy evaluation algorithm is developed for the case of experience re-use. We address the question of sufficient experience for uniform convergence of policy evaluation and obtain sample complexity bounds for various estimators. Finally, we demonstrate the performance of the proposed algorithms on several domains, the most complex of which is simulated adaptive packet routing in a telecommunication network.

The World Administrative Radio Conference and international communications policy : hearings before the Subcommittee on International Operations of the Committee on Foreign Affairs, House of Representatives, Ninety-sixth Congress, June 14, 1979, and July 31, 1980.

Mode of access: Internet.

Methods for conflict resolution in policy-based management systems

While developments in distributed object computing environments, such as the Common Object Request Broker Architecture (CORBA) [17] and the Telecommunication Intelligent Network Architecture (TINA) [16], have enabled interoperability between domains in large open distributed systems, managing the resources within such systems has become an increasingly complex task. This challenge has been considered for several years within the distributed systems management research community and policy-based management has recently emerged as a promising solution. Large evolving enterprises present a significant challenge for policy-based management partly due to the requirement to support both mutual transparency and individual autonomy between domains [2], but also because the fluidity and complexity of interactions occurring within such environments requires an ability to cope with the coexistence of multiple, potentially inconsistent policies. This paper discusses the need of providing both dynamic (run-time) and static (compile-time) conflict detection and resolution for policies in such systems and builds on our earlier conflict detection work [7, 8] to introduce the methods for conflict resolution in large open distributed systems.

Standard Essential Patent in Telecommunication Standard: United States and China Comparison

Thesis (Ph.D.)--University of Washington, 2016-08

Work/Family Balance: HRM Policy and Practice in Australia

An employee's inability to balance work and family responsibilities has resulted in an increase in stress related illnesses. Historically, research into the nexus between work and family has primarily focused on the work/family conflict relationship, predominately investigating the impact of this conflict on parents, usually mothers. To date research has not sufficiently examined the human resource management practices that enable all parents to achieve a balance between their work and family lives. This paper explores the relationship between contemporary family friendly HRM policies and employed parents perceptions of work/family enhancement, work/family satisfaction, propensity to turnover, and work/family conflict. Self-report questionnaire data from 326 men and women is analysed and discussed to enable organisations to consider the use of family friendly policies and thus create a convergence between the well-being of employees and the effectiveness of the organisation.