Search

There is increasing awareness in the planning community that depending on complete models impedes the applicability of planning technology in many real world domains where the burden of specifying complete domain models is too high. In this paper, we consider the problem of generating robust and accurate plans, when the agent only has access to incomplete domain models, supplanted by a set of successful plan cases. We will develop two classes of approaches – one case-based and the other model-based. ML-CBP is a case-based approach that leverages the incomplete model and the plan cases to solve a new problem directly by affecting case-level transfer. RIM is a model-based approach that uses the incomplete model and the plan cases to first learn a more complete model. This model contains both primitive actions as well as macro-operators that are derived from the plan cases. The learned model is then used in conjunction with an off-the-shelf planner to solve new problems. We present a comprehensive evaluation of the two approaches, both to characterize their relative tradeoffs, and to quantify their advances over existing approaches. [ABSTRACT FROM AUTHOR]

Abstract: Applying learning techniques to acquire action models is an area of intense research interest. Most previous work in this area has assumed that there is a significant amount of training data available in a planning domain of interest. However, it is often difficult to acquire sufficient training data to ensure the learnt action models are of high quality. In this paper, we seek to explore a novel algorithm framework, called TRAMP, to learn action models with limited training data in a target domain, via transferring as much of the available information from other domains (called source domains) as possible to help the learning task, assuming action models in source domains can be transferred to the target domain. TRAMP transfers knowledge from source domains by first building structure mappings between source and target domains, and then exploiting extra knowledge from Web search to bridge and transfer knowledge from sources. Specifically, TRAMP first encodes training data with a set of propositions, and formulates the transferred knowledge as a set of weighted formulas. After that it learns action models for the target domain to best explain the set of propositions and the transferred knowledge. We empirically evaluate TRAMP in different settings to see their advantages and disadvantages in six planning domains, including four International Planning Competition (IPC) domains and two synthetic domains. [Copyright &y& Elsevier]

This paper proposes a novel approach based on the planning-graph to solve the top-k QoS-aware automatic composition problem of semantic Web services. The approach includes three sequential stages: a forward search stage to generate a planning-graph to reduce the search space of the following two stages greatly, an optimal local QoS calculating stage to compute all the optimal local QoS values of services in the planning, and a backward search stage to find the top-K composed services with optimal QoS values according to the planning-graph and the optimal QoS value. In order to validate the approach, experiments are carried out based on the test sets offered by the WS-Challenge competition 2009. The results show that the approach can find the same optimal solution as the champion system from the competition but also can provide more alternative solutions with the optimal QoS for users. [ABSTRACT FROM AUTHOR]

Abstract: In recent years, a number of new heuristic search methods have been developed in the field of automated planning. Enforced hill climbing (EHC) is one such method which has been frequently used in a number of AI planning systems. Despite certain weaknesses, such as getting trapped in dead-ends in some domains, this method is more competitive than several other methods in many planning domains. In order to enhance the efficiency of ordinary enforced hill climbing, a new form of enforced hill climbing, called guided enforced hill climbing, is introduced in this paper. An adaptive branch ordering function is the main feature that guided enforced hill climbing has added to EHC. Guided enforced hill climbing expands successor states in the order recommended by the ordering function. Our experimental results in several planning domains show a significant improvement in the efficiency of the enforced hill climbing method, especially when applied to larger problems. [ABSTRACT FROM AUTHOR]

Adaptive automated planning systems that can, over time, improve the quality of plans they produce are a promising prospect. The first part of the article discusses the issues involved in designing quality improving learning for planning systems and reviews recent work on learning to improve plan quality. The second part describes our work on the Performance Improving Planning (PIP) System. The heart of PIP is an analytic technique that compares two planning episodes for solving a planning problem that led to two different quality solutions—a higher-quality solution and a lower quality solution—and identifies the critical differences that were responsible for the resulting differences in the quality of the completed plans. We compare the effectiveness of two different ways of storing and applying the knowledge learned from this analysis—as search-control rules and as rewrite rules. The results show that the search-control rules are more effective in improving plan quality. Further analysis of PIP-search-control—the version of PIP that stores the learned knowledge as search-control rules—shows that it is an effective technique for improving plan quality in a variety of situations. [ABSTRACT FROM AUTHOR]

AI planning systems tend to be disembodied and are not situated within the environment for which plans are generated, thus losing information concerning the interaction between the system and its environment. This paper argues that such information may potentially be valuable in constraining plan formulation, and presents both an agent- and domain-independent architecture that extends the classical AI planning framework to take into account context, or the interaction between an autonomous situated planning agent and its environment. The paper describes how context constrains the goals an agent might generate, enables those goals to be prioritised, and constrains plan selection. [ABSTRACT FROM AUTHOR]

Constraint satisfaction is a fundamental Artificial Intelligence technique for knowledge representation and inference. However, the formulation of a static constraint satisfaction problem (CSP) with hard, imperative constraints is insufficient to model many real problems. Fuzzy constraint satisfaction provides a more graded viewpoint. Priorities and preferences are placed on individual constraints and aggregated via fuzzy conjunction to obtain a satisfaction degree for a solution to the problem. This paper examines methods for solving an important instance of dynamic flexible constraint satisfaction (DFCSP) combining fuzzy CSP and restriction/relaxation based dynamic CSP: fuzzy rrDFCSP. This allows the modelling of complex situations where both the set of constraints may change over time and there is flexibility inherent in the definition of the problem. This paper also presents a means by which classical planning can be extended via fuzzy sets to enable flexible goals and preferences to be placed on the use of planning operators. A range of plans can be produced, trading compromises made versus the length of the plan. The flexible planning operators are close in definition to fuzzy constraints. Hence, through a hierarchical decomposition of the planning graph, the work shows how flexible planning reduces to the solution of a set of fuzzy rrDFCSPs. [Copyright &y& Elsevier]