http://user.it.uu.se/~jarst116/slides/week4.pdf

Graph-Based Algorithms for Boolean Function Manipulation

Learning action models with minimal observability

Efficient symbolic search for cost-optimal planning

Sequential planning portfolios are very powerful in exploiting the complementary strength of different automated planners. The main challenge of a portfolio planner is to define which base planners to run, to assign the running time for each planner and to decide in what order they should be carried out to optimize a planning metric. Portfolio configurations are usually derived empirically from training benchmarks and remain fixed for an evaluation phase. In this work, we create a per-instance configurable portfolio, which is able to adapt itself to every planning task. The proposed system pre-selects a group of candidate planners using a Pareto-dominance filtering approach and then it decides which planners to include and the time assigned according to predictive models. These models estimate whether a base planner will be able to solve the given problem and, if so, how long it will take. We define different portfolio strategies to combine the knowledge generated by the models. The experimental evaluation shows that the resulting portfolios provide an improvement when compared with non-informed strategies. One of the proposed portfolios was the winner of the Sequential Satisficing Track of the International Planning Competition held in 2014.

/pdf/the-ibacop-planning-system-instance-based-configured-a3f4q41oce.pdf

The IBaCoP planning system: instance-based configured portfolios

The International Planning Competition (IPC) is a prominent event of the artificial intelligence planning community that has been organized since 1998; it aims at fostering the development and comparison of planning approaches, assessing the state-of-the-art in planning and identifying new challenging benchmarks. IPC has a strong impact also outside the planning community, by providing a large number of ready-to-use planning engines and testing pioneering applications of planning techniques.This paper focusses on the deterministic part of IPC 2014, and describes format, participants, benchmarks as well as a thorough analysis of the results. Generally, results of the competition indicates some significant progress, but they also highlight issues and challenges that the planning community will have to face in the future.

/pdf/what-you-always-wanted-to-know-about-the-deterministic-part-2s66ce1s4b.pdf

What you always wanted to know about the deterministic part of the International Planning Competition (IPC) 2014 (but were too afraid to ask)

The deterministic part of the seventh International Planning Competition

Landmarks are one of the most effective search heuristics for classical planning, but largely ignored in generalized planning. Generalized planning (GP) is usually addressed as a combinatorial search in a given space of algorithmic solutions, where candidate solutions are evaluated w.r.t. the instances they solve. This type of solution evaluation ignores any sub-goal information that is not explicit in the representation of the planning instances, causing plateaus in the space of candidate generalized plans. Furthermore, node expansion in GP is a run-time bottleneck since it requires evaluating every child node over the entire batch of classical planning instances in a GP problem. In this paper we define a landmark counting heuristic for GP (that considers sub-goal information that is not explicitly represented in the planning instances), and a novel heuristic search algorithm for GP (that we call PGP) and that progressively processes subsets of the planning instances of a GP problem. Our two orthogonal contributions are analyzed in an ablation study, showing that both improve the state-of-the-art in GP as heuristic search, and that both benefit from each other when used in combination.

Scaling-up Generalized Planning as Heuristic Search with Landmarks

This chapter reports the last machine learning techniques for the assistance of automated planning. Recent discoveries in automated planning have opened the scope of planners, from toy problems to real-world applications, making new challenges come into focus. The planning community believes that machine learning can assist to address these new challenges. The chapter collects the last machine learning techniques for assisting automated planners classified in: techniques for the improvement of the planning search processes and techniques for the automatic definition of planning action models. For each technique, the chapter provides an in-depth analysis of their domain, advantages and disadvantages. Finally, the chapter draws the outline of the new promising avenues for research in learning for planning systems.

Improving Automated Planning with Machine Learning

Automated Planning (AP) studies the generation of action sequences for problem solving. A problem in AP is defined by a state-transition function describing the dynamics of the world, the initial state of the world and the goals to be achieved. According to this definition, AP problems seem to be easily tackled by searching for a path in a graph, which is a well-studied problem. However, the graphs resulting from AP problems are so large that explicitly specifying them is not feasible. Thus, different approaches have been tried to address AP problems. Since the mid 90’s, new planning algorithms have enabled the solution of practical-size AP problems. Nevertheless, domain-independent planners still fail in solving complex AP problems, as solving planning tasks is a PSPACE-Complete problem (Bylander, 94). How do humans cope with this planning-inherent complexity? One answer is that our experience allows us to solve problems more quickly; we are endowed with learning skills that help us plan when problems are selected from a stable population. Inspire by this idea, the field of learning-based planning studies the development of AP systems able to modify their performance according to previous experiences. Since the first days, Artificial Intelligence (AI) has been concerned with the problem of Machine Learning (ML). As early as 1959, Arthur L. Samuel developed a prominent program that learned to improve its play in the game of checkers (Samuel, 1959). It is hardly surprising that ML has often been used to make changes in systems that perform tasks associated with AI, such as perception, robot control or AP. This article analyses the diverse ways ML can be used to improve AP processes. First, we review the major AP concepts and summarize the main research done in learning-based planning. Second, we describe current trends in applying ML to AP. Finally, we comment on the next avenues for combining AP and ML and conclude.

Learning-Based Planning

Planning as heuristic search is one of the most successful approaches to classical planning but unfortunately, it does not extend trivially to Generalized Planning (GP). GP aims to compute algorithmic solutions that are valid for a set of classical planning instances from a given domain, even if these instances differ in the number of objects, the number of state variables, their domain size, or their initial and goal configuration. The generalization requirements of GP make it impractical to perform the state-space search that is usually implemented by heuristic planners. This paper adapts the planning as heuristic search paradigm to the generalization requirements of GP, and presents the first native heuristic search approach to GP. First, the paper introduces a new pointer-based solution space for GP that is independent of the number of classical planning instances in a GP problem and the size of those instances (i.e. the number of objects, state variables and their domain sizes). Second, the paper defines a set of evaluation and heuristic functions for guiding a combinatorial search in our new GP solution space. The computation of these evaluation and heuristic functions does not require grounding states or actions in advance. Therefore our GP as heuristic search approach can handle large sets of state variables with large numerical domains, e.g. integers. Lastly, the paper defines an upgraded version of our novel algorithm for GP called Best-First Generalized Planning (BFGP), that implements a best-first search in our pointer-based solution space, and that is guided by our evaluation/heuristic functions for GP.

Sergio Jiménez Celorrio

Papers

The deterministic part of the seventh International Planning Competition

Scaling-up Generalized Planning as Heuristic Search with Landmarks

Improving Automated Planning with Machine Learning

Learning-Based Planning

Generalized Planning as Heuristic Search: A new planning search-space that leverages pointers over objects