A SAT-based approach to cost-sensitive temporally expressive planning

Lü, Qiang; Huang, Ruoyun; Chen, Yixin; Xu, Yingcheng; Zhang, Weixiong; Chen, Guoliang

doi:10.1145/2542182.2542200

Cited by 3 publications

(5 citation statements)

References 43 publications

(71 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method follows the bounded SAT solving strategy, originally proposed in SATPlan Kautz and Selman (1992) and Graphplan Blum and Furst (1997). It starts from a lower bound of makespan (L=1), encodes the SAS+ problem as a weighted partial Max-SAT (WPMax-SAT) instance Lu et al (2014), and either proves it unsatisfiable or finds a plan while trying to minimize total action costs at the same time.…”

Section: Definition 12 (State Similarity) the Similarity Between Two ...mentioning

confidence: 99%

Extracting Actionability from Machine Learning Models by Sub-optimal Deterministic Planning

Lyu,

Chen,

et al. 2016

Preprint

Self Cite

View full text Add to dashboard Cite

A main focus of machine learning research has been improving the generalization accuracy and efficiency of prediction models. Many models such as SVM, random forest, and deep neural nets have been proposed and achieved great success. However, what emerges as missing in many applications is actionability, i.e., the ability to turn prediction results into actions. For example, in applications such as customer relationship management, clinical prediction, and advertisement, the users need not only accurate prediction, but also actionable instructions which can transfer an input to a desirable goal (e.g., higher profit repays, lower morbidity rates, higher ads hit rates). Existing effort in deriving such actionable knowledge is few and limited to simple action models which restricted to only change one attribute for each action. The dilemma is that in many real applications those action models are often more complex and harder to extract an optimal solution.In this paper, we propose a novel approach that achieves actionability by combining learning with planning, two core areas of AI. In particular, we propose a framework to extract actionable knowledge from random forest, one of the most widely used and best off-the-shelf classifiers. We formulate the actionability problem to a sub-optimal action planning (SOAP) problem, which is to find a plan to alter certain features of a given input so that the random forest would yield a desirable output, while minimizing the total costs of actions. Technically, the SOAP problem is formulated in the SAS+ planning formalism, and solved using a Max-SAT based approach. Our experimental results demonstrate the effectiveness and efficiency of the proposed approach on a personal credit dataset and other benchmarks. Our work represents a new application of automated planning on an emerging and challenging machine learning paradigm.

show abstract

Section: Definition 12 (State Similarity) the Similarity Between Two ...mentioning

confidence: 99%

Extracting Actionability from Machine Learning Models by Sub-optimal Deterministic Planning

Lyu,

Chen,

et al. 2016

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since time is a continuous quantity, it cannot be treated in the exact same way in which discrete causality is handled. To tackle this problem, STEP (Huang, Chen, & Zhang, 2009), SCP2 (Lu, Huang, Chen, Xu, Zhang, & Chen, 2013), and T-SATPLAN (Mali & Liu, 2006) use a discrete representation of time. These planners assign explicit discrete time labels to each step of the encoding.…”

Section: Related Workmentioning

confidence: 99%

“…This drawback of the explicit time representation causes STEP, SCP2, and T-SATPLAN to be inefficient in terms of both speed and memory usage. To obtain a better performance, SCP2 uses ∃-step semantic to allow causal relations between actions in each time point (Lu et al, 2013). TM-LPSAT (Shin & Davis, 2005), which has been designed to solve planning problems defined in PDDL+ , is another SAT-based planner capable of handling temporal planning problems.…”

Section: Related Workmentioning

confidence: 99%

“…Because of the similarities between the approach used in ITSAT and that of SCP2 (Lu et al, 2013), we have also included the results of this planner in our experimental results.…”

Section: Itsat Versus the State-of-the-art Temporal Plannersmentioning

confidence: 99%

“…SCP2 (Lu et al, 2013), is a SAT-based temporal planner that uses a discrete representation of time. This planner assigns explicit discrete time labels to each step of the encoding.…”

Section: Itsat Versus the State-of-the-art Temporal Plannersmentioning

confidence: 99%

See 2 more Smart Citations

ITSAT: An Efficient SAT-Based Temporal Planner

Rankooh¹,

Ghassem-Sani²

2015

jair

View full text Add to dashboard Cite

Planning as satisfiability is known as an efficient approach to deal with many types of planning problems. However, this approach has not been competitive with the state-space based methods in temporal planning. This paper describes ITSAT as an efficient SAT-based (satisfiability based) temporal planner capable of temporally expressive planning. The novelty of ITSAT lies in the way it handles temporal constraints of given problems without getting involved in the difficulties of introducing continuous variables into the corresponding satisfiability problems. We also show how, as in SAT-based classical planning, carefully devised preprocessing and encoding schemata can considerably improve the efficiency of SAT-based temporal planning. We present two preprocessing methods for mutex relation extraction and action compression. We also show that the separation of causal and temporal reasoning enables us to employ compact encodings that are based on the concept of parallel execution semantics. Although such encodings have been shown to be quite effective in classical planning, ITSAT is the first temporal planner utilizing this type of encoding. Our empirical results show that not only does ITSAT outperform the state-of-the-art temporally expressive planners, it is also competitive with the fast temporal planners that cannot handle required concurrency.

show abstract