On the recognition of abstract Markov policies

Abstraction plays an essential role in the way the agents plan their behaviours, especially to reduce the computational complexity of planning in large domains. However, the effects of abstraction in the inverse process – plan recognition – are unclear. In this paper, we present a method for recognising the agent’s behaviour in noisy and uncertain domains, and across multiple levels of abstraction. We use the concept of abstract Markov policies in abstract probabilistic planning as the model of the agent’s behaviours and employ probabilistic inference in Dynamic Bayesian Networks (DBN) to infer the correct policy from a sequence of observations. When the states are fully observable, we show that for a broad and often-used class of abstract policies, the complexity of policy recognition scales well with the number of abstraction levels in the policy hierarchy. For the partially observable case, we derive an efficient hybrid inference scheme on the corresponding DBN to overcome the exponential complexity.

Hierarchical monitoring of people's behaviors in complex environments using multiple cameras

We present a distributed, surveillance system that works in large and complex indoor environments. To track and recognize behaviors of people, we propose the use of the Abstract Hidden Markov Model (AHMM), which can be considered as an extension of the Hidden Markov Model (HMM), where the single Markov chain in the HMM is replaced by a hierarchy of Markov policies. In this policy hierarchy, each behavior can be represented as a policy at the corresponding level of abstraction. The noisy observations are handled in the same way as an HMM and an efficient Rao-Blackwellised particle filter method is used to compute the probabilities of the current policy at different levels of the hierarchy The novelty of the paper lies in the implementation of a scalable framework in the context of both the scale of behaviors and the size of the environment, making it ideal for distributed surveillance. The results of the system demonstrate the ability to answer queries about people's behaviors at different levels of details using multiple cameras in a large and complex indoor environment.

Avoiding giving advice in telephone counselling for children and young people

Kids Helpline is an Australian 24-hour telephone counselling helpline for children and young people up to the age of 25 years old. The service operates with the core values of empowerment for clients, and the use of child-centred practices, one aspect of which is a non-directive approach highlighted by the avoidance of overt advice giving. Through analysis of a single call to the helpline, this chapter demonstrates how counsellors actively manage and minimise the normative and asymmetric properties of advice in the course if helping clients develop options for change. In doing so we illustrate the practical relevance and enactment of abstract institutional policies and discuss the interactional affordances of institutional constraints on practice.

Los mercados en el Istmo Centroamericano y México: ¿qué ha pasado con la competencia?

Incluye Bibliografía

Um olhar sobre os colegiados dos territórios da cidadania no Pará

No Brasil, as políticas territoriais e, em particular, os Territórios da Cidadania, representam inovações institucionais interessantes. A avaliação e o melhoramento delas necessitam de uma análise dos mecanismos diferenciados da ação pública, e suas consequências concretas sobre as formas de territórios resultantes. A partir do exemplo do estado do Pará, a relação entre a diversidade de dinâmicas territoriais e o funcionamento diferenciado dos colegiados dos Territórios da Cidadania é analisada, a partir do nível de participação, da eficiência deles como espaço de governança e da implementação de projetos de investimento. Os problemas específicos e os aspectos positivos dos colegiados são analisados e explicados. Perspectivas metodológicas e de desenvolvimentos são sugeridas para melhorar o programa.

Inventário e análise sociológica das políticas públicas de turismo em Angola

As políticas públicas na área do turismo tornaram-se uma prioridade dos governos dos países desenvolvidos e menos desenvolvidos a partir da década de 1970, quando os organismos estatais ligados ao sector do turismo deram início à definição de amplas agendas nacionais para o desenvolvimento da indústria do turismo para períodos de longo prazo, com descrições claras sobre a posição que o turismo ocupa no âmbito do desenvolvimento da economia nacional; sobre as metas que se pretendem alcançar e a forma como elas serão atingidas. O enorme crescimento do turismo, o envolvimento dos governos e os impactos negativos do turismo que foram registados nos países em desenvolvimento ajudou a trazer ao debate académico a análise sobre as políticas públicas do turismo no final dos anos 80 e início de 90 do séc. passado. Neste estudo inventariou-se o quadro legislativo das políticas públicas do turismo em Angola e fez-se o enquadramento sociológico da Política Nacional e do Plano Diretor do turismo em Angola; identificaram-se os atores que intervêm na execução das políticas públicas do turismo em Angola e o seu sentido social, assim como os fatores centrais propiciadores do desenvolvimento social e económico em contexto local (Huíla). Isto permitiu determinar o perfil e tipologias resultantes da contribuição do quadro de Políticas Públicas de turismo para o nível de promoção do desenvolvimento social local em Angola, ajudando-nos a tentar perceber até que ponto as políticas públicas do turismo em Angola se constituem como fator de desenvolvimento social local. Partindo do perfil e tipologias resultantes da contribuição do quadro de Políticas Públicas de turismo e com base nos resultados obtidos através da análise de conteúdo das entrevistas, construiu-se uma proposta de modelo de políticas públicas de turismo propiciadoras do desenvolvimento local sustentável em Angola baseada numa lógica de ação coletiva, capaz de salvaguardar a sustentabilidade económica, política, social e territorial; ABSTRACT: Public policies in tourism became a priority of developed country governments and less developed countries from the 1970s, when the state bodies linked to the tourism sector began the definition of a broad national agenda for the development of the tourism industry for long-term periods, with clear descriptions of the position that tourism occupies in the national economic development; on the goals they want to achieve and how they will be achieved. The tremendous growth of tourism, the involvement of governments and the negative impacts of tourism were registered in developing countries and helped to bring the academic debate analysis on public tourism policies, in the late 80s and early 90s of the past century. In the legislative framework, we inventoried public tourism policies in Angola that later became the sociological framework of the National Policy and Plan for tourism in Angola; we identified the actors involved in the execution of public tourism policies in Angola and its social meaning, as well as the central factors conductive to social and economic development in the local context (Huila). This allowed to determine the profile and types resulting from the tourism Public Policy framework contribution to the level of promotion of local social development in Angola, helping us in this way to try to understand to what extent public tourism policies in Angola work as a local social development factor. From the profile and types resulting from the tourism Public Policy framework contribution and based on the results obtained from the interviews, we constructed a proposed model of public policies which encourage a more sustainable local development kind of tourism in Angola, based on a logic of collective action, able to safeguard the economic, political, social and territorial capitals.

Policy recognition in the Abstract Hidden Markov Model

In this paper, we present a method for recognising an agent's behaviour in dynamic, noisy, uncertain domains, and across multiple levels of abstraction. We term this problem on-line plan recognition under uncertainty and view it generally as probabilistic inference on the stochastic process representing the execution of the agent's plan. Our contributions in this paper are twofold. In terms of probabilistic inference, we introduce the Abstract Hidden Markov Model (AHMM), a novel type of stochastic processes, provide its dynamic Bayesian network (DBN) structure and analyse the properties of this network. We then describe an application of the Rao-Blackwellised Particle Filter to the AHMM which allows us to construct an efficient, hybrid inference method for this model. In terms of plan recognition, we propose a novel plan recognition framework based on the AHMM as the plan execution model. The Rao-Blackwellised hybrid inference for AHMM can take advantage of the independence properties inherent in a model of plan execution, leading to an algorithm for online probabilistic plan recognition that scales well with the number of levels in the plan hierarchy. This illustrates that while stochastic models for plan execution can be complex, they exhibit special structures which, if exploited, can lead to efficient plan recognition algorithms. We demonstrate the usefulness of the AHMM framework via a behaviour recognition system in a complex spatial environment using distributed video surveillance data.

Tracking and surveillance in wide-area spatial environments using the abstract hidden markov model.

In this paper, we consider the problem of tracking an object and predicting the object's future trajectory in a wide-area environment, with complex spatial layout and the use of multiple sensors/cameras. To solve this problem, there is a need for representing the dynamic and noisy data in the tracking tasks, and dealing with them at different levels of detail. We employ the Abstract Hidden Markov Models (AHMM), an extension of the well-known Hidden Markov Model (HMM) and a special type of Dynamic Probabilistic Network (DPN), as our underlying representation framework. The AHMM allows us to explicitly encode the hierarchy of connected spatial locations, making it scalable to the size of the environment being modeled. We describe an application for tracking human movement in an office-like spatial layout where the AHMM is used to track and predict the evolution of object trajectories at different levels of detail.

Enforcing P3P policies using a digital rights management system

The protection of privacy has gained considerable attention recently. In response to this, new privacy protection systems are being introduced. SITDRM is one such system that protects private data through the enforcement of licenses provided by consumers. Prior to supplying data, data owners are expected to construct a detailed license for the potential data users. A license specifies whom, under what conditions, may have what type of access to the protected data. The specification of a license by a data owner binds the enterprise data handling to the consumer’s privacy preferences. However, licenses are very detailed, may reveal the internal structure of the enterprise and need to be kept synchronous with the enterprise privacy policy. To deal with this, we employ the Platform for Privacy Preferences Language (P3P) to communicate enterprise privacy policies to consumers and enable them to easily construct data licenses. A P3P policy is more abstract than a license, allows data owners to specify the purposes for which data are being collected and directly reflects the privacy policy of an enterprise.

Bounded parameter Markov Decision Processes with average reward criterion

Bounded parameter Markov Decision Processes (BMDPs) address the issue of dealing with uncertainty in the parameters of a Markov Decision Process (MDP). Unlike the case of an MDP, the notion of an optimal policy for a BMDP is not entirely straightforward. We consider two notions of optimality based on optimistic and pessimistic criteria. These have been analyzed for discounted BMDPs. Here we provide results for average reward BMDPs. We establish a fundamental relationship between the discounted and the average reward problems, prove the existence of Blackwell optimal policies and, for both notions of optimality, derive algorithms that converge to the optimal value function.

The enterprise information security policy as a strategic business policy within the corporate strategic plan (extended abstract)

Information security has been recognized as a core requirement for corporate governance that is expected to facilitate not only the management of risks, but also as a corporate enabler that supports and contributes to the sustainability of organizational operations. In implementing information security, the enterprise information security policy is the set of principles and strategies that guide the course of action for the security activities and may be represented as a brief statement that defines program goals and sets information security and risk requirements. The enterprise information security policy (alternatively referred to as security policy in this paper) that represents the meta-policy of information security is an element of corporate ICT governance and is derived from the strategic requirements for risk management and corporate governance. Consistent alignment between the security policy and the other corporate business policies and strategies has to be maintained if information security is to be implemented according to evolving business objectives. This alignment may be facilitated by managing security policy alongside other corporate business policies within the strategic management cycle. There are however limitations in current approaches for developing and managing the security policy to facilitate consistent strategic alignment. This paper proposes a conceptual framework for security policy management by presenting propositions to positively affect security policy alignment with business policies and prescribing a security policy management approach that expounds on the propositions.

Linear programming for large-scale Markov decision problems

We consider the problem of controlling a Markov decision process (MDP) with a large state space, so as to minimize average cost. Since it is intractable to compete with the optimal policy for large scale problems, we pursue the more modest goal of competing with a low-dimensional family of policies. We use the dual linear programming formulation of the MDP average cost problem, in which the variable is a stationary distribution over state-action pairs, and we consider a neighborhood of a low-dimensional subset of the set of stationary distributions (defined in terms of state-action features) as the comparison class. We propose a technique based on stochastic convex optimization and give bounds that show that the performance of our algorithm approaches the best achievable by any policy in the comparison class. Most importantly, this result depends on the size of the comparison class, but not on the size of the state space. Preliminary experiments show the effectiveness of the proposed algorithm in a queuing application.

Ergodic control of partially observed Markov chains

The ergodic or long-run average cost control problem for a partially observed finite-state Markov chain is studied via the associated fully observed separated control problem for the nonlinear filter. Dynamic programming equations for the latter are derived, leading to existence and characterization of optimal stationary policies.

Asymptotic behaviour of point processes with Markov-dependent intervals

This splitting techniques for MARKOV chains developed by NUMMELIN (1978a) and ATHREYA and NEY (1978b) are used to derive an imbedded renewal process in WOLD's point process with MARKOV-correlated intervals. This leads to a simple proof of renewal theorems for such processes. In particular, a key renewal theorem is proved, from which analogues to both BLACKWELL's and BREIMAN's forms of the renewal theorem can be deduced.