scholarly journals Inferring Time-delayed Causal Relations in POMDPs from the Principle of Independence of Cause and Mechanism

2021 ◽  
Author(s):  
Junchi Liang ◽  
Abdeslam Boularias
Keyword(s):  
Information Gain ◽  
Hidden Variables ◽  
Causal Link ◽  
Causal Relations ◽  
Monte Carlo Tree Search ◽  
3D Game ◽  
Confounding Variables ◽  
Markov Assumption ◽  
Data Efficiency ◽  
Robotic Tasks

This paper introduces an algorithm for discovering implicit and delayed causal relations between events observed by a robot at regular or arbitrary times, with the objective of improving data-efficiency and interpretability of model-based reinforcement learning (RL) techniques. The proposed algorithm initially predicts observations with the Markov assumption, and incrementally introduces new hidden variables to explain and reduce the stochasticity of the observations. The hidden variables are memory units that keep track of pertinent past events. Such events are systematically identified by their information gains. A test of independence between inputs and mechanisms is performed to identify cases when there is a causal link between events and those when the information gain is due to confounding variables. The learned transition and reward models are then used in a Monte Carlo tree search for planning. Experiments on simulated and real robotic tasks, and the challenging 3D game Doom show that this method significantly improves over current RL techniques.

scholarly journals Causal Relations of Upscaled Urban Aquaponics and the Food-Water-Energy Nexus—A Berlin Case Study

Water ◽  
2021 ◽  
Vol 13 (15) ◽  
pp. 2029
Author(s):  
Gösta F.M. Baganz ◽  
Manfred Schrenk ◽  
Oliver Körner ◽  
Daniela Baganz ◽  
Karel J. Keesman ◽  
...  
Keyword(s):  
Urban Areas ◽  
Causal Link ◽  
Supply Side ◽  
Demand Side ◽  
Annual Fish ◽  
Causal Relations ◽  
Water Energy Nexus ◽  
Facility Level ◽  
Predominant Effect

Aquaponics, the water-reusing production of fish and crops, is taken as an example to investigate the consequences of upscaling a nature-based solution in a circular city. We developed an upscaled-aquaponic scenario for the German metropolis of Berlin, analysed the impacts, and studied the system dynamics. To meet the annual fish, tomato, and lettuce demand of Berlin’s 3.77 million residents would require approximately 370 aquaponic facilities covering a total area of 224 hectares and the use of different combinations of fish and crops: catfish/tomato (56%), catfish/lettuce (13%), and tilapia/tomato (31%). As a predominant effect, in terms of water, aquaponic production would save about 2.0 million m3 of water compared to the baseline. On the supply-side, we identified significant causal link chains concerning the Food-Water-Energy nexus at the aquaponic facility level as well as causal relations of a production relocation to Berlin. On the demand-side, a ‘freshwater pescatarian diet’ is discussed. The new and comprehensive findings at different system levels require further investigations on this topic. Upscaled aquaponics can produce a relevant contribution to Berlin’s sustainability and to implement it, research is needed to find suitable sites for local aquaponics in Berlin, possibly inside buildings, on urban roofscape, or in peri-urban areas.

scholarly journals Data Efficient Reinforcement Learning for Integrated Lateral Planning and Control in Automated Parking System

Sensors ◽  
2020 ◽  
Vol 20 (24) ◽  
pp. 7297
Author(s):  
Shaoyu Song ◽  
Hui Chen ◽  
Hongwei Sun ◽  
Meicen Liu
Keyword(s):  
Reinforcement Learning ◽  
Path Following ◽  
Monte Carlo Tree Search ◽  
Integrated Method ◽  
Model Based ◽  
Planning And Control ◽  
Model Free ◽  
Data Efficiency ◽  
And Control ◽  
Path Following Methods

Reinforcement learning (RL) is a promising direction in automated parking systems (APSs), as integrating planning and tracking control using RL can potentially maximize the overall performance. However, commonly used model-free RL requires many interactions to achieve acceptable performance, and model-based RL in APS cannot continuously learn. In this paper, a data-efficient RL method is constructed to learn from data by use of a model-based method. The proposed method uses a truncated Monte Carlo tree search to evaluate parking states and select moves. Two artificial neural networks are trained to provide the search probability of each tree branch and the final reward for each state using self-trained data. The data efficiency is enhanced by weighting exploration with parking trajectory returns, an adaptive exploration scheme, and experience augmentation with imaginary rollouts. Without human demonstrations, a novel training pipeline is also used to train the initial action guidance network and the state value network. Compared with path planning and path-following methods, the proposed integrated method can flexibly co-ordinate the longitudinal and lateral motion to park a smaller parking space in one maneuver. Its adaptability to changes in the vehicle model is verified by joint Carsim and MATLAB simulation, demonstrating that the algorithm converges within a few iterations. Finally, experiments using a real vehicle platform are used to further verify the effectiveness of the proposed method. Compared with obtaining rewards using simulation, the proposed method achieves a better final parking attitude and success rate.

Causal relations and the surrogate mother.

1976 ◽  
Vol 31 (9) ◽  
pp. 671-673
Author(s):  
James Forest
Keyword(s):  
Surrogate Mother ◽  
Causal Relations

The Adaptation of Medical Records to Epidemiological Use

1965 ◽  
Vol 04 (03) ◽  
pp. 136-140
Author(s):  
Cl Jeanty
Keyword(s):  
Medical Records ◽  
Clinical Pathology ◽  
Time Variable ◽  
Special Care ◽  
General Description ◽  
Causal Relations ◽  
Laboratory Techniques ◽  
Original Record ◽  
Statistical Studies

A method is described in an attempt to make medical records suitable for epidemiologigri: purposes. Every case of a disease is recorded on an appropriate punched card with the object of working towards a general description of a disease through the collation of several cases of the same diagnosis. This punched card represents a very great condensation of the original record. Special care has been applied to state as precisely as possible the time variable, particularly as far as its origin and unit of measure are concerned, in order to demonstrate the existence of causal relations between diseases. Such cards are also intended to make easier statistical studies in clinical pathology, in evaluation of new laboratory techniques, and in therapeutical trials.

PENENTUAN DAERAH PRIORITAS PELAYANAN AKTA KELAHIRAN DENGAN METODE K-NN DAN K-MEANS

2020 ◽  
Vol 17 (1) ◽  
pp. 319-328
Author(s):  
Ade Muchlis Maulana Anwar ◽  
Prihastuti Harsani ◽  
Aries Maesya
Keyword(s):  
Nearest Neighbor ◽  
Information Gain ◽  
Birth Certificate ◽  
Population Data ◽  
Community Services ◽  
Birth Certificates ◽  
Similar Data ◽  
K Nearest Neighbor ◽  
Civil Registration ◽  
The Family

Population Data is individual data or aggregate data that is structured as a result of Population Registration and Civil Registration activities. Birth Certificate is a Civil Registration Deed as a result of recording the birth event of a baby whose birth is reported to be registered on the Family Card and given a Population Identification Number (NIK) as a basis for obtaining other community services. From the total number of integrated birth certificate reporting for the 2018 Population Administration Information System (SIAK) totaling 570,637 there were 503,946 reported late and only 66,691 were reported publicly. Clustering is a method used to classify data that is similar to others in one group or similar data to other groups. K-Nearest Neighbor is a method for classifying objects based on learning data that is the closest distance to the test data. k-means is a method used to divide a number of objects into groups based on existing categories by looking at the midpoint. In data mining preprocesses, data is cleaned by filling in the blank data with the most dominating data, and selecting attributes using the information gain method. Based on the k-nearest neighbor method to predict delays in reporting and the k-means method to classify priority areas of service with 10,000 birth certificate data on birth certificates in 2019 that have good enough performance to produce predictions with an accuracy of 74.00% and with K = 2 on k-means produces a index davies bouldin of 1,179.

Sign in / Sign up

Export Citation Format

Share Document