Inspired by game theory representations, Bayesian networks, influence diagrams, structured Markov decision process models, logic programming, and work in dynamical systems, the independent choice logic (ICL) is a semantic framework that allows for independent choices (made by various agents, including nature) and a logic program that gives the consequence of choices. This representation can be used as a specification for agents that act in a world, make observations of that world and have memory, as well as a modelling tool for dynamic environments with uncertainty. The rules specify the consequences of an action, what can be sensed and the utility of outcomes. This paper presents a possible-worlds semantics for ICL, and shows how to embed influence diagrams, structured Markov decision processes, and both the strategic (normal) form and extensive (game-tree) form of games within the Thanks to Craig Boutilier and Holger Hoos for detailed comments on this paper. This work was supporte...

This paper describes Autominder, a cognitive orthotic system intended to help older adults adapt to cognitive decline and continue the satisfactory performance of routine activities, thereby potentially enabling them to remain in their own homes longer. Autominder achieves this goal by providing adaptive, personalized reminders of (basic, instrumental, and extended) activities of daily living. Cognitive orthotic systems on the market today mainly provide alarms for prescribed activities at fixed times that are specified in advance. In contrast, Autominder uses a range of AI techniques to model an individual's daily plans, observe and reason about the execution of those plans, and make decisions about whether and when it is most appropriate to issue reminders. Autominder is currently deployed on a mobile robot, and is being developed as part of the Initiative on Personal Robotic Assistants for the Elderly (the Nursebot project)

Intelligent agency requires some ability to predict the future. An agent must ask itself what is presently its best course of action given what it now knows about what the world will be like when it intends to act. This paper presents a system that uses a probabilistic model to reason about the effects of an agent's proposed actions on a dynamic and uncertain world, computing the probability that relevant propositions will hold at a specified point in time. The model allows for incomplete information about the world, the occurrence of exogenous (unplanned) events, unreliable sensors, and the possibility of an imperfect causal theory. The system provides an application program with answers to questions of the form "is the probability that ' will hold in the world at time t greater than ø ?" It is unique among algorithms for probabilistic temporal reasoning in that it tries to limit its inference according to the proposition, time, and probability threshold provided by the application. T...

This paper is about how to represent and solve decision problems in Bayesian decision theory (e.g. [6]). A general representation named decision networks is proposed based on influence diagrams [10]. This new representation incorporates the idea, from Markov decision process (e.g. [5]), that a decision may be conditionally independent of certain pieces of available information. It also allows multiple cooperative agents and facilitates the exploitation of separability in the utility function. Decision networks inherit the advantages of both influence diagrams and Markov decision processes, which makes them a better representation framework for decision analysis, planning under uncertainty, medical diagnosis and treatment.

Temporal interpolation is the task of bridging gaps between time-oriented concepts in a context-sensitive manner. It is a subtask important for solving the temporal-abstraction task---abstraction of interval-based, higher-level concepts from time-stamped data.

We develop a probability forecasting model through a synthesis of Bayesian beliefnetwork models and classical time-series analysis. By casting Bayesian time-series analyses as temporal belief-network problems, weintroduce dependency models that capture richer and more realistic models of dynamic dependencies. With richer models and associated computational methods, we can movebeyond the rigid classical assumptions of linearityin the relationships among variables and of normality of their probability distributions.

We present a language for representing context-sensitive temporal probabilistic knowledge. Context constraints allow inference to be focused on only the relevant portions of the probabilistic knowledge. We provide a declarative semantics for our language. We present a sound and complete algorithm for computing posterior probabilities of temporal queries, as well as an efficient implementation of the algorithm. Throughout we illustrate the approach with the problem of reasoning about the effects of medications and interventions on the state of a patient in cardiac arrest. We empirically evaluate the efficiency of our system by comparing its inference times on problems in this domain with those of standard Bayesian network representations of the problems. Keywords: Temporal probability models, Bayesian networks, Logic programming, Prognostic evaluation 1 Introduction For accurate medical diagnosis and prediction, it is often necessary to model a patient's condition over time. Because th...

A computational system for reasoning about dynamic time-sliced systems using Bayesian networks is presented. The system, called dHugin, may be viewed as a generalization of the inference methods of classical discrete time-series analysis in the sense that it allows description of non-linear, discrete multivariate dynamic systems with complex conditional independence structures. The paper introduces the notions of dynamic time-sliced Bayesian networks, a dynamic time window, and common operations on the time window. Inference, pertaining to the time window and time slices preceding it, are formulated in terms of the well-known message passing scheme in junction trees [Jensen et al. (1990)]. Backward smoothing, for example, are performed efficiently through inter-tree message passing. Further, the system provides an ecient Monte-Carlo algorithm for forecasting; i.e., inference pertaining to time slices succeeding the time window. The system has been implemented on top of the Hugin shell [Andersen et al. (1989)].

To date, there has been no work on temporal probabilistic agent reasoning on top of heterogeneous legacy databases and software modules. We will define the concept of a heterogeneous temporal probabilistic (HTP) agent. Such agents can be built on top of existing databases, data structures, and software code bases without explicitly accessing the internal code of those systems and can take actions compatible with a policy or operating principles specified by an agent developer. We will develop a formal semantics for such agents through the notion of a feasible temporal probabilistic status interpretation (FTPSI for short). Intuitively, an FTPSI specifies what all an HTP agent is permitted/forbidden/obliged to do at various times t. As changes occur in the environment, the HTP agent must compute a new FTPSI. HTP agents continuously compute FTPSI’s in order to determine what they should do and hence, the problem of computing FTPSI’s is very important. We give a sound and complete algorithm to compute FTPSI’s for a very large class of HTP agents called strict HTP agents. In a given state, many FTPSI’s may exist. These represent alternative courses of action that the HTP agent can take. We provide a notion of an optimal FTPSI that selects an FTPSI optimising an objective function and give a sound and complete algorithm to

Systems that are subject to uncertainty in their behaviour are often modelled by Bayesian Belief Networks (BBNs). These are probabilistic models of the system in which the independence relations between the variables of interest are represented explicitly. A directed graph is used, in which two nodes are connected by an edge if one is a 'direct cause' of the other. However the Bayesian paradigm does not provide any direct means for modelling dynamic systems. There has been a considerable amount of research effort in recent years to address this. This paper reviews these approaches and proposes a new dynamic extension to the BBN. This paper proceeds to discuss fault management of complex telecommunications and how the dynamic bayesian models can assist in the prediction of faults. Keywords: dynamic bayesian belief networks, telecommunication networks, fault management, intelligent systems. 1