The evolution of the electronic sources connected through wide area networks like Internet has encouraged the development of new information gathering techniques that go beyond traditional information retrieval and WEB search methods. They use advanced techniques, like planning or constraint programming, to integrate and reason about hetereogeneous information sources. In this paper we describe MAPWEB. MAPWEB is a multiagent framework that integrates planning agents and WEB information retrieval agents. The goal of this framework is to deal with problems that require planning with information to be gathered from the WEB. MAPWEB decouples planning from information gathering, by splitting a planning problem into two parts: solving an abstract problem and validating and completing the abstract solutions by means of information gathering. This decoupling allows also to address an important aspect of information gathering: the WEB is a dynamic medium and more and more companies make their information available in the WEB everyday. The MAPWEB framework can be adapted quickly to these changes by just modifying the planning domain and adding the required information gathering agents. For instance, in a travel assistant domain, if taxi companies begin to offer WEB information, it would only be necessary to add new planning operators related to traveling by taxi, for a more complete travel domain. This paper describes the MAPWEB planning process, focusing on the aforementioned flexibility aspect.

GBFS-based satisficing planners often augment their search with knowledge-based enhancements such as preferred operators and multiple heuristics. These techniques seek to improve planner performance by making the search more informed. In our work, we will focus on how these enhancements impact coverage and we will use a simple technique called epsilon-greedy node selection to demonstrate that planner coverage can also be improved by introducing knowledge-free random exploration into the search. We then revisit the existing knowledge-based enhancements so as to determine if the knowledge these enhancements employ is offering necessary guidance, or if the impact of this knowledge is to add exploration which can be achieved more simply using randomness. This investigation provides further evidence of the importance of preferred operators and shows that the knowledge added when using an additional heuristic is crucial in certain domains, while not being as effective as random exploration in others. Finally, we demonstrate that random exploration can also improve the coverage of LAMA, a planner which already employs multiple enhancements. This suggests that knowledge-based enhancements need to be compared to appropriate knowledge-free random baselines so as to ensure the importance of the knowledge being used.

This paper summarizes the main existing approaches to propagate resource constraints in Constraint-Based scheduling and identifies some of their limitations for using them in an integrated planning and scheduling framework. We then describe two new algorithms to propagate resource constraints on discrete resources and reservoirs. Unlike most of the classical work in scheduling, our algorithms focus on the precedence relations between activities rather than on their absolute position in time. They are efficient even when the set of activities is not completely defined and when the time window of activities is large. These features explain why our algorithms are particularly suited for integrated planning and scheduling approaches. All our algorithms are illustrated with examples. Encouraging preliminary results are reported on pure scheduling problems.

We introduce a family of MDP reduced models characterized by two parameters: the maximum number of primary outcomes per action that are fully accounted for and the maximum number of occurrences of the remaining exceptional outcomes that are planned for in advance. Reduced models can be solved much faster using heuristic search algorithms such as LAO*, benefiting from the dramatic reduction in the number of reachable states. A commonly used determinization approach is a special case of this family of reductions, with one primary outcome per action and zero exceptional outcomes per plan. We present a framework to compute the benefits of planning with reduced models, relying on online planning when the number of exceptional outcomes exceeds the bound. Using this framework, we compare the performance of various reduced models and consider the challenge of generating good ones automatically. We show that each one of the dimensions---allowing more than one primary outcome or planning for some limited number of exceptions---could improve performance relative to standard determinization. The results place recent work on determinization in a broader context and lay the foundation for efficient and systematic exploration of the space of MDP model reductions.

Estimating the distance from a current partial-order plan to the goal state of the plan task is a challenging problem, with past research achieving only limited success. In an effort to understand the reasons for this situation, we investigate the computational complexity of the partial-order plan viability problem. We define several boundaries between the tractable and intractable subclasses of the problem, from which we identify several constraints that contribute to the computational intractability of the problem. These results bring new insights into the design and the development of future  partial-order planning heuristics.

We present a scalable fully-automated forward-chaining planner capable of reasoning with PDDL+ events and linear processes.  Processes and events model (respectively) continuous and discrete exogenous activity in the environment, occurring when certain conditions hold.  We discuss the significant challenges posed in creating a planner that can reason with these, and present novel state-progression and consistency enforcing techniques that allow us to meet these challenges.  We present results showing that our new planner, using PDDL+ models, is able to solve realistic expressive problems more efficiently than the state-of-the-art alternative: a compiled PDDL 2.1 representation with continuous numeric effects.

Real-time search methods, such as LRTA*, have been used to solve awide variety of planning problems because they can make decisions fastand still converge to a minimum-cost plan if they solve the sameplanning task repeatedly. In this paper, we perform an empiricalevaluation of two existing variants of LRTA* that were developed tospeed up its convergence, namely HLRTA* and FALCONS. Our experimentalresults demonstrate that these two real-time search methods havecomplementary strengths and can be combined. We call the new real-timesearch method eFALCONS and show that it converges with fewer actionsto a minimum-cost plan than LRTA*, HLRTA*, and FALCONS.

Applications that require alternative plans challenge the single solution, single quality metric assumptions upon which many classical planners are designed and evaluated. To evaluate the distinctness of alternative plans (i.e., plan sets), researchers have created diversity metrics that often measure the set difference between the actions of plans. Many approaches for generating plan sets embed the same diversity metric in a weighted evaluation function to guide the search mechanism, thus confounding the search process with its evaluation. We discover that two diversity metrics fail to distinguish similar plans from each other or to identify plans with extraneous actions, so we introduce two new diversity metrics, \emph{uniqueness} and \emph{overlap}, to capture these cases. We then examine the tradeoffs of producing diverse plans while we control for plan length and metric interaction and confirm that metric interaction can significantly impact search performance. We show that planners searching for plan sets must consider a third metric, \emph{parsimony}, that prefers shorter plans while maximizing diversity.We evaluate three existing approaches for generating diverse plans and two new algorithms that are designed to explicitly manage diversity and interaction between the diversity and quality metrics. Our findings synthesize and extend recent results in plan diversity.

Finding optimal policies for Markov Decision Processes with large state spaces is in general intractable. Nonetheless, simulation-based algorithms inspired by Sparse Sampling (SS) such as Upper Confidence Bound applied in Trees (UCT) and Forward Search Sparse Sampling (FSSS) have been shown to perform reasonably well in both theory and practice, despite the high computational demand. To improve the efficiency of these algorithms, we adopt a simple enhancement technique with a heuristic policy to speed up the selection of optimal actions. The general method, called Aux, augments the look-ahead tree with auxiliary arms that are evaluated by the heuristic policy. In this paper, we provide theoretical justification for the method and demonstrate its effectiveness in two experimental benchmarks that showcase the faster convergence to a near optimal policy for both SS and FSSS. Moreover, to further speed up the convergence of these algorithms at the early stage, we present a novel mechanism to combine them with UCT so that the resulting hybrid algorithm is superior to both of its components.

Many heuristics for cost-optimal planning are based on linear programming. We cover several interesting heuristics of this type by a common framework that fixes the objective function of the linear program. Within the framework, constraints from different heuristics can be combined in one heuristic estimate which dominates the maximum of the component heuristics. Different heuristics of the framework can be compared on the basis of their constraints. With this new method of analysis, we show dominance of the recent LP-based state-equation heuristic over optimal cost partitioning on single-variable abstractions.  We also show that the previously suggested extension of the state-equation heuristic to exploit safe variables cannot lead to an improved heuristic estimate. We experimentally evaluate the potential of the proposed framework on an extensive suite of benchmark tasks.