scholarly journals The IBaCoP Planning System: Instance-Based Configured Portfolios

2016 ◽  
Vol 56 ◽  
pp. 657-691 ◽  
Author(s):  
Isabel Cenamor ◽  
Tomás De la Rosa ◽  
Fernando Fernández
Keyword(s):  
Predictive Models ◽  
Planning System ◽  
Pareto Dominance ◽  
Portfolio Strategies ◽  
Main Challenge ◽  
Evaluation Phase ◽  
Planning Task ◽  
International Planning ◽  
The Given ◽  
Filtering Approach

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.

scholarly journals The Metric-FF Planning System: Translating ``Ignoring Delete Lists'' to Numeric State Variables

2003 ◽  
Vol 20 ◽  
pp. 291-341 ◽  
Author(s):  
J. Hoffmann
Keyword(s):  
Natural Extension ◽  
Planning System ◽  
State Variables ◽  
Heuristic Function ◽  
Planning Task ◽  
Algorithmic Techniques ◽  
International Planning

Planning with numeric state variables has been a challenge for many years, and was a part of the 3rd International Planning Competition (IPC-3). Currently one of the most popular and successful algorithmic techniques in STRIPS planning is to guide search by a heuristic function, where the heuristic is based on relaxing the planning task by ignoring the delete lists of the available actions. We present a natural extension of ``ignoring delete lists'' to numeric state variables, preserving the relevant theoretical properties of the STRIPS relaxation under the condition that the numeric task at hand is ``monotonic''. We then identify a subset of the numeric IPC-3 competition language, ``linear tasks'', where monotonicity can be achieved by pre-processing. Based on that, we extend the algorithms used in the heuristic planning system FF to linear tasks. The resulting system Metric-FF is, according to the IPC-3 results which we discuss, one of the two currently most efficient numeric planners.

scholarly journals Efficient Lifted Planning with Regression-Based Heuristics

2021 ◽  
Author(s):  
Hadi Qovaizi
Keyword(s):  
Organic Synthesis ◽  
State Of The Art ◽  
Transition System ◽  
Modern State ◽  
Synthetic Approach ◽  
Best First Search ◽  
Planning Task ◽  
International Planning ◽  
Domain Independent ◽  
Novel Algorithm

Modern state-of-the-art planners operate by generating a grounded transition system prior to performing search for a solution to a given planning task. Some tasks involve a significant number of objects or entail managing predicates and action schemas with a significant number of arguments. Hence, this instantiation procedure can exhaust all available memory and therefore prevent a planner from performing search to find a solution. This thesis explores this limitation by presenting a benchmark set of problems based on Organic Chemistry Synthesis that was submitted to the latest International Planning Competition (IPC-2018). This benchmark was constructed to gauge the performance of the competing planners given that instantiation is an issue. Furthermore, a novel algorithm, the Regression-Based Heuristic Planner (RBHP), is developed with the aim of averting this issue. RBHP was inspired by the retro-synthetic approach commonly used to solve organic synthesis problems efficiently. RBHP solves planning tasks by applying domain independent heuristics, computed by regression, and performing best-first search. In contrast to most modern planners, RBHP computes heuristics backwards by applying the goal-directed regression operator. However, the best-first search proceeds forward similar to other planners. The proposed planner is evaluated on a set of planning tasks included in previous International Planning Competitions (IPC) against a subset of the top scoring state-of-the-art planners submitted to the IPC-2018.

scholarly journals A Special Report on 2019 International Planning Competition and a Comprehensive Analysis of Its Results

2020 ◽  
Vol 10 ◽  
Author(s):  
Jiayun Chen ◽  
Jianrong Dai ◽  
Ahmad Nobah ◽  
Sen Bai ◽  
Nan Bi ◽  
...  
Keyword(s):  
Work Experience ◽  
Medical Physics ◽  
Large Population ◽  
Locally Advanced ◽  
Planning System ◽  
Treatment Planning System ◽  
Plan Quality ◽  
Wide Range ◽  
The Mean ◽  
International Planning

PurposeThe aim of this work is to introduce the 2019 International Planning Competition and to analyze its results.Methods and materialsA locally advanced non-small cell lung cancer (LA-NSCLC) case using the simultaneous integrated boost approach was selected. The plan quality was evaluated by using a ranking system in accordance with practice guidelines. Planners used their clinical Treatment Planning System (TPS) to generate the best possible plan along with a survey, designed to obtain medical physics aspects information. We investigated the quality of the large population of plans designed by worldwide planners using different planning and delivery systems. The correlations of plan quality with relevant planner characteristics (work experience, department scale, and competition experience) and with technological parameters (TPS and modality) were examined.ResultsThe number of the qualified plans was 287 with a wide range of scores (38.61–97.99). The scores showed statistically significant differences by the following factors: 1) department scale: the mean score (89.76 ± 8.36) for planners from the departments treating >2,000 patients annually was the highest of all; 2) competition experience: the mean score for the 107 planners with previous competition experience was 88.92 ± 9.59, statistically significantly from first-time participants (p = .001); 3) techniques: the mean scores for planners using VMAT (89.18 ± 6.43) and TOMO (90.62 ± 7.60) were higher than those using IMRT (82.28 ± 12.47), with statistical differences (p <.001). The plan scores were negligibly correlated with the planner’s years of work experience or the type of TPS used. Regression analysis demonstrated that plan score was associated with dosimetric objectives that were difficult to achieve, which is generally consistent with a clinical practice evaluation. However, 51.2% of the planners abandoned the difficult component of total lung receiving a dose of 5 Gy in their plan design to achieve the optimal plan.ConclusionThe 2019 international planning competition was carried out successfully, and its results were analyzed. Plan quality was not correlated with work experiences or the TPS used, but it was correlated with department scale, modality, and competition experience. These findings differed from those reported in previous studies.

scholarly journals Friends or Foes? On Planning as Satisfiability and Abstract CNF Encodings

2009 ◽  
Vol 36 ◽  
pp. 415-469 ◽  
Author(s):  
C. Domshlak ◽  
J. Hoffmann ◽  
A. Sabharwal
Keyword(s):  
Point Of View ◽  
Theoretical Point ◽  
Optimal Plan ◽  
Interesting Phenomenon ◽  
State Spaces ◽  
Planning Task ◽  
Resolution Refutation ◽  
International Planning ◽  
Almost All ◽  
Planning Graph

Planning as satisfiability, as implemented in, for instance, the SATPLAN tool, is a highly competitive method for finding parallel step-optimal plans. A bottleneck in this approach is to *prove the absence* of plans of a certain length. Specifically, if the optimal plan has N steps, then it is typically very costly to prove that there is no plan of length N-1. We pursue the idea of leading this proof within solution length preserving abstractions (over-approximations) of the original planning task. This is promising because the abstraction may have a much smaller state space; related methods are highly successful in model checking. In particular, we design a novel abstraction technique based on which one can, in several widely used planning benchmarks, construct abstractions that have exponentially smaller state spaces while preserving the length of an optimal plan. Surprisingly, the idea turns out to appear quite hopeless in the context of planning as satisfiability. Evaluating our idea empirically, we run experiments on almost all benchmarks of the international planning competitions up to IPC 2004, and find that even hand-made abstractions do not tend to improve the performance of SATPLAN. Exploring these findings from a theoretical point of view, we identify an interesting phenomenon that may cause this behavior. We compare various planning-graph based CNF encodings F of the original planning task with the CNF encodings F_abs of the abstracted planning task. We prove that, in many cases, the shortest resolution refutation for F_abs can never be shorter than that for F. This suggests a fundamental weakness of the approach, and motivates further investigation of the interplay between declarative transition-systems, over-approximating abstractions, and SAT encodings.

scholarly journals Eliminating Latent Discrimination: Train Then Mask

2019 ◽  
Vol 33 ◽  
pp. 3672-3680
Author(s):  
Soheil Ghili ◽  
Ehsan Kazemi ◽  
Amin Karbasi
Keyword(s):  
Decision Making ◽  
Supervised Learning ◽  
Predictive Models ◽  
Test Evaluation ◽  
Training Phase ◽  
Small Loss ◽  
Omitted Variable Bias ◽  
Evaluation Phase ◽  
Variable Bias

How can we control for latent discrimination in predictive models? How can we provably remove it? Such questions are at the heart of algorithmic fairness and its impacts on society. In this paper, we define a new operational fairness criteria, inspired by the well-understood notion of omitted variable-bias in statistics and econometrics. Our notion of fairness effectively controls for sensitive features and provides diagnostics for deviations from fair decision making. We then establish analytical and algorithmic results about the existence of a fair classifier in the context of supervised learning. Our results readily imply a simple, but rather counter-intuitive, strategy for eliminating latent discrimination. In order to prevent other features proxying for sensitive features, we need to include sensitive features in the training phase, but exclude them in the test/evaluation phase while controlling for their effects. We evaluate the performance of our algorithm on several realworld datasets and show how fairness for these datasets can be improved with a very small loss in accuracy.

scholarly journals TALplanner in IPC-2002: Extensions and Control Rules

2003 ◽  
Vol 20 ◽  
pp. 343-377 ◽  
Author(s):  
J. Kvarnström ◽  
M. Magnusson
Keyword(s):  
Temporal Logic ◽  
Domain Knowledge ◽  
Search Space ◽  
Planning System ◽  
Short Introduction ◽  
The Third ◽  
Control Rules ◽  
Benchmark Tests ◽  
International Planning ◽  
And Control

TALplanner is a forward-chaining planner that relies on domain knowledge in the shape of temporal logic formulas in order to prune irrelevant parts of the search space. TALplanner recently participated in the third International Planning Competition, which had a clear emphasis on increasing the complexity of the problem domains being used as benchmark tests and the expressivity required to represent these domains in a planning system. Like many other planners, TALplanner had support for some but not all aspects of this increase in expressivity, and a number of changes to the planner were required. After a short introduction to TALplanner, this article describes some of the changes that were made before and during the competition. We also describe the process of introducing suitable domain knowledge for several of the competition domains.

scholarly journals Molecular optimization by capturing chemist’s intuition using deep neural networks

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Jiazhen He ◽  
Huifang You ◽  
Emil Sandström ◽  
Eva Nittinger ◽  
Esben Jannik Bjerrum ◽  
...  
Keyword(s):  
Machine Translation ◽  
Language Processing ◽  
Deep Neural Networks ◽  
Chemical Transformations ◽  
Proof Of Concept ◽  
Matched Molecular Pairs ◽  
Main Challenge ◽  
Property Changes ◽  
Transformer Model ◽  
The Given

AbstractA main challenge in drug discovery is finding molecules with a desirable balance of multiple properties. Here, we focus on the task of molecular optimization, where the goal is to optimize a given starting molecule towards desirable properties. This task can be framed as a machine translation problem in natural language processing, where in our case, a molecule is translated into a molecule with optimized properties based on the SMILES representation. Typically, chemists would use their intuition to suggest chemical transformations for the starting molecule being optimized. A widely used strategy is the concept of matched molecular pairs where two molecules differ by a single transformation. We seek to capture the chemist’s intuition from matched molecular pairs using machine translation models. Specifically, the sequence-to-sequence model with attention mechanism, and the Transformer model are employed to generate molecules with desirable properties. As a proof of concept, three ADMET properties are optimized simultaneously: logD, solubility, and clearance, which are important properties of a drug. Since desirable properties often vary from project to project, the user-specified desirable property changes are incorporated into the input as an additional condition together with the starting molecules being optimized. Thus, the models can be guided to generate molecules satisfying the desirable properties. Additionally, we compare the two machine translation models based on the SMILES representation, with a graph-to-graph translation model HierG2G, which has shown the state-of-the-art performance in molecular optimization. Our results show that the Transformer can generate more molecules with desirable properties by making small modifications to the given starting molecules, which can be intuitive to chemists. A further enrichment of diverse molecules can be achieved by using an ensemble of models.

scholarly journals Molecular Optimization by Capturing Chemist’s Intuition Using Deep Neural Networks

2020 ◽  
Author(s):  
Jiazhen He ◽  
huifang you ◽  
Emil Sandström ◽  
eva nittinger ◽  
Esben Jannik Bjerrum ◽  
...  
Keyword(s):  
Machine Translation ◽  
Language Processing ◽  
Deep Neural Networks ◽  
Chemical Transformations ◽  
Proof Of Concept ◽  
Matched Molecular Pairs ◽  
Main Challenge ◽  
Property Changes ◽  
Transformer Model ◽  
The Given

A main challenge in drug discovery is finding molecules with a desirable balance of multiple properties. Here, we focus on the task of molecular optimization, where the goal is to optimize a given starting molecule towards desirable properties. This task can be framed as a machine translation problem in natural language processing, where in our case, a molecule is translated into a molecule with optimized properties based on the SMILES representation. Typically, chemists would use their intuition to suggest chemical transformations for the starting molecule being optimized. A widely used strategy is the concept of matched molecular pairs where two molecules differ by a single transformation. We seek to capture the chemist's intuition from matched molecular pairs using machine translation models. Specifically, the sequence-to-sequence model with attention mechanism, and the Transformer model are employed to generate molecules with desirable properties. As a proof of concept, three ADMET properties are optimized simultaneously: <i>logD</i>, <i>solubility</i>, and <i>clearance</i>, which are important properties of a drug. Since desirable properties often vary from project to project, the user-specified desirable property changes are incorporated into the input as an additional condition together with the starting molecules being optimized. Thus, the models can be guided to generate molecules satisfying the desirable properties. Additionally, we compare the two machine translation models based on the SMILES representation, with a graph-to-graph translation model HierG2G, which has shown the state-of-the-art performance in molecular optimization. Our results show that the Transformer can generate more molecules with desirable properties by making small modifications to the given starting molecules, which can be intuitive to chemists. A further enrichment of diverse molecules can be achieved by using an ensemble of models.

scholarly journals Investments in Renewable Energy Sources in the Concepts of Local Spatial Policy: The Case of Poland

Energies ◽  
2021 ◽  
Vol 14 (23) ◽  
pp. 7902
Author(s):  
Małgorzata Blaszke ◽  
Maciej Nowak ◽  
Przemysław Śleszyński ◽  
Bartosz Mickiewicz
Keyword(s):  
Renewable Energy ◽  
Renewable Energy Sources ◽  
Policy Instruments ◽  
Spatial Development ◽  
Interesting Case ◽  
Planning System ◽  
Energy Sources ◽  
Spatial Policy ◽  
Development Plans ◽  
The Given

The paper aims to determine the role and formula of investments in renewable energy sources in Poland’s concepts of local spatial policies. It analyses 12,777 planning documents of local spatial policy (these are resolutions adopted by municipalities—in Poland there are two types of these instruments: studies of spatial development conditions and directions and local spatial development plans) in Poland enacted in 2005–2020. On this basis, local concepts were classified and related to the geographical and functional characteristics of municipalities. Poland is an interesting case study in this respect, providing a good reference point for broader international considerations. It was found that only 58.4% of Polish municipalities include renewable energy sources in their spatial policy concept. These are definitely more often urbanised municipalities. The degree of approach to renewable energy sources is also determined by the location of the municipality in the given province. The authors diagnose serious weaknesses in the Polish spatial planning system, consisting in the lack of skilful implementation of renewable energy sources into it. This is one of the reasons for the weaker development of renewable energy sources in the country. The authors consider as an innovative element of the research the analysis of the content of all spatial policy instruments in a given country, from the perspective of renewable energy sources, including proposing a way to verify these instruments.

scholarly journals Molecular Optimization by Capturing Chemist's Intuition Using Deep Neural Networks

2020 ◽  
Author(s):  
Jiazhen He ◽  
Huifang You ◽  
Emil Sandström ◽  
Eva Nittinger ◽  
Esben Bjerrum ◽  
...  
Keyword(s):  
Machine Translation ◽  
Language Processing ◽  
Deep Neural Networks ◽  
Chemical Transformations ◽  
Proof Of Concept ◽  
Matched Molecular Pairs ◽  
Main Challenge ◽  
Property Changes ◽  
Transformer Model ◽  
The Given

Abstract A main challenge in drug discovery is finding molecules with a desirable balance of multiple properties. Here, we focus on the task of molecular optimization, where the goal is to optimize a given starting molecule towards desirable properties. This task can be framed as a machine translation problem in natural language processing, where in our case, a molecule is translated into a molecule with optimized properties based on the SMILES representation. Typically, chemists would use their intuition to suggest chemical transformations for the starting molecule being optimized. A widely used strategy is the concept of matched molecular pairs where two molecules differ by a single transformation. We seek to capture the chemist's intuition from matched molecular pairs using machine translation models. Specifically, the sequence-to-sequence model with attention mechanism, and the Transformer model are employed to generate molecules with desirable properties. As a proof of concept, three ADMET properties are optimized simultaneously: logD, solubility, and clearance, which are important properties of a drug. Since desirable properties often vary from project to project, the user-specified desirable property changes are incorporated into the input as an additional condition together with the starting molecules being optimized. Thus, the models can be guided to generate molecules satisfying the desirable properties. Additionally, we compare the two machine translation models based on the SMILES representation, with a graph-to-graph translation model HierG2G, which has shown the state-of-the-art performance in molecular optimization. Our results show that the Transformer can generate more molecules with desirable properties by making small modifications to the given starting molecules, which can be intuitive to chemists. A further enrichment of diverse molecules can be achieved by using an ensemble of models.

Sign in / Sign up

Export Citation Format

Share Document