Improving Automated Planning with Machine Learning (original) (raw)

A review of machine learning for automated planning

The Knowledge Engineering Review, 2012

Recent discoveries in automated planning are broadening the scope of planners, from toy problems to real applications. However, applying automated planners to real-world problems is far from simple. On the one hand, the definition of accurate action models for planning is still a bottleneck. On the other hand, off-the-shelf planners fail to scale-up and to provide good solutions in many domains. In these problematic domains, planners can exploit domain-specific control knowledge to improve their performance in terms of both speed and quality of the solutions. However, manual definition of control knowledge is quite difficult. This paper reviews recent techniques in machine learning for the automatic definition of planning knowledge. It has been organized according to the target of the learning process: automatic definition of planning action models and automatic definition of planning control knowledge. In addition, the paper reviews the advances in the related field of reinforcemen...

Progress in AI planning research and applications

Upgrade, 2002

Planning has made significant progress since its inception in the 1970s, in terms both of the efficiency and sophistication of its algorithms and representations and its potential for application to real problems. In this paper we sketch the foundations of planning as a sub-field of Artificial Intelligence and the history of its development over the past three decades. Then some of the recent achievements within the field are discussed and provided some experimental data demonstrating the progress that has been made in the application of ...

Unveiling the Potential of Machine Learning Applications in Urban Planning Challenges

Land

In a digitalized era and with the rapid growth of computational skills and advancements, artificial intelligence and Machine Learning uses in various applications are gaining a rising interest from scholars and practitioners. As a fast-growing field of Artificial Intelligence, Machine Artificial Intelligence deals with smart designs, data mining and management for complex problem-solving based on experimental data on urban applications (land use and cover, configurations of the built environment and architectural design, etc.), but with few explorations and relevant studies. In this work, a comprehensive and in-depth review is presented to discuss the future opportunities and constraints in meeting the next planning portfolio against the multiple challenges in urban environments in line with Machine Learning progress. Bringing together the theoretical views with practical analyses of cases and examples, the work unveils the huge potential, but also the potential barriers of the comp...

1 Developments in AI Planning Research

An intelligent agent should be able to decide upon a course of actions to achieve certain goals. A plan is such a course of actions and the planning problem is the problem of f inding a plan for a given representation of actions in the world the agent operates in. In this paper, we provide a survey of the developments in AI planning research, with an emphasis on recent techniques. Introduction, Background and Early Work: An intelligent agent should be able to decide upon a course of actions to achieve certain goals. A plan is such a course of actions and the planning problem is the problem of f inding a plan for a given representation of actions in the world the agent operates in. GPS (general problem solver) was the first planner to distinguish between general problemsolving knowledge and domain knowledge. It introduced means-end analysis in its search procedure. This approach tried to find a difference between the current object and the goal, and then used a lookup table to invoke...

Towards adaptive heuristic planning through machine learning

2002

In domain independent heuristic planning there is a number of planning systems with very good performance on some problems and very poor on others. Few attempts have been made in the past to explain this phenomenon. In this paper we use machine learning techniques to discover knowledge hidden in the dynamics of the planning process that would relate specific characteristics of a planning problem with specific properties of a planning system that lead to good or bad performance. By this, we aim at shedding light to some of the dark areas of heuristic planning and develop an adaptive planner that would be able to optimize its configuration according to the problem at hand.

Unsupervised Classification of Planning Instances

International Conference on Automated Planning and Scheduling, 2017

In this paper we introduce a novel approach for unsupervised classification of planning instances based on the recent formalism of planning programs. Our approach is inspired by structured prediction in machine learning, which aims at predicting structured information about a given input rather than a scalar value. In our case, each input is an unlabelled classical planning instance, and the associated structured information is the planning program that solves the instance. We describe a method that takes as input a set of planning instances and outputs a set of planning programs, classifying each instance according to the program that solves it. Our results show that automated planning can be successfully used to solve structured unsupervised classification tasks, and invites further exploration of the connection between automated planning and structured prediction.

Are automated planners up to solve real problems

2008

Abstract: It is a well known fact that the AI planning community is very committed to apply the developments already achieved in this area to real complex applications. However realistic planning problems bring great challenges not only for the designers during design processes but also for the automated planners during the planning process itself. In addition, it is quite common to face issues about whether the available planners will be up to solve the problem being modeled during the initial design stages.

Exploring the Synergy between Two Modular Learning Techniques for Automated Planning

2015

In the last decade the emphasis on improving the operational performance of domain independent automated planners has been in developing complex techniques which merge a range of different strategies. This quest for operational advantage, driven by the regular international planning competitions, has not made it easy to study, understand and predict what combinations of techniques will have what effect on a planner’s behaviour in a particular application domain. In this paper, we consider two machine learning techniques for planner performance improvement, and exploit a modular approach to their combination in order to facilitate the analysis of the impact of each individual component. We believe this can contribute to the development of more transparent planning engines, which are designed using modular, interchangeable, and well-founded components. Specifically, we combined two previously unrelated learning techniques, entanglements and relational decision trees, to guide a “vanil...