Abstract: According to one embodiment, a method, computer system, and computer program product for probabilistic inference from imprecise knowledge is provided. The embodiment may include identifying a knowledge base of one or more statements and first probability distributions corresponding to each of the one or more statements. The embodiment may also include identifying one or more queries. The embodiment may further include determining logical inferences about and second probability distributions for queries from the one or more queries or statements from the one or more statements based on information in the knowledge base.

Abstract: A method for computing possibly optimal policies in reinforcement learning with multiple objectives and tradeoffs includes receiving a dataset comprising state, action, and reward information for objectives in a multiple objective environment. Tradeoff information indicating that a first vector comprising first values of the objectives in the multiple objective environment is preferred to a second vector comprising second values of the objectives in the multiple objective environment is received. A set of possibly optimal policies for the multiple objective environment is produced based on the dataset and the tradeoff information, where the set of possibly optimal policies indicates actions for an intelligent agent operating in the multiple objective environment to take.

Abstract: Various embodiments are provided for intelligent application of operational rules to operational data in a computing environment by a processor. One or more operational rules may be extracted and formalized from a knowledge graph, a domain knowledge, or a combination thereof describing one or more operational policies and conditions. The one or more operational rules may be applied to operational data to identify and filter non-compliant operational data.

Abstract: In an approach for recommending a safe path for people to navigate an environment, a processor generates a contact graph for a user in a group of users in an area, based on a pre-defined distance measurement between the user and another user in a same timestamp during a pre-defined time period. A processor builds a profile for the user based on the contact graph, the profile including a probability model corresponding to the contact graph to estimate an infection probability for the user. A processor calculates an initial route for the user from a first location to a second location in the area. A processor analyzes an infection risk for the user based on the profile and other users within a pre-defined distance to the user in the initial route. A processor updates the initial route based on the analysis to minimize the risk to be infected.

Abstract: According to one embodiment, a method, computer system, and computer program product for reinforcement learning is provided. The present invention may include training, using an offline dataset, a plurality of diverse reward models, and creating a policy based on an output of the reward models and a robustness operator of the reward models.

Abstract: Embodiments are provided for providing enhanced routing in a computing system by a processor. All first-order logic formulas may be converted into real-valued logic formulas. A probabilistic inference is executed using the real-valued logic formulas and one or more probability intervals associated with an atomic formulae in a knowledge base to provide an interval conditional probability indicating that a first predicate condition is true based one or more alternative predicates being true.

Abstract: In an approach to predictive contact tracing, a computer receives a query associated with contact tracing of a person with an infection. A computer retrieves timestamped location data associated with the person over a period of time. Based on the retrieved data, a computer creates a contact graph associated with the person, where the contact graph depicts one or more other people that were in contact with the person over the period of time. A computer retrieves medical data associated with the person and the one or more other people that were in contact with the person over the period of time. Based on the retrieved data, a computer builds a probabilistic model. A computer runs the probabilistic model to provide a prediction of a probability of infection of the one or more other people over the period of time as a result of being in contact with the person.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to facilitating code development by predicting one or more code attributes and/or code portions for use in a project code to be written. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise a dialogue component that generates a query based on a natural language request comprising a code-related attribute, and a prediction component that predicts another attribute or a code portion to satisfy the request. In an embodiment, an input dataset employed to support the influence mapping can comprise time-stamped tuple data comprising a state, an action and a reward. The code-related attribute can at least partially define a project code, of code to be written.

Abstract: One or more systems, devices, computer program products and/or computer-implemented methods of use provided herein relate to outputting an optimal decision policy base on informal knowledge input. A system can comprise a memory that stores computer executable components, and a processor that executes the computer executable components stored in the memory, wherein the computer executable components can comprise an analysis component that analyzes an input dataset comprising a constraint in a natural language form, and an augmentation component that generates an influence mapping comprising a constraint variable based on the constraint input. In an embodiment, an input dataset employed to support the influence mapping can comprise time-stamped tuple data comprising a state, an action and a reward. In an embodiment, an inference engine can generate an output policy in response to the constraint input and which output policy can be based on the constraint input and constraint variable.

Abstract: Systems, computer-implemented methods and/or computer program products that facilitate answering questions that involve mathematical computations are provided. In one embodiment, a computer-implemented method comprises: transforming, by a system operatively coupled to a processor, a natural language query into a first logical representation and extrinsic knowledge into a second logical representation relevant to the natural language query; merging, by the system, the first logical representation and the second logical representation into a third logical representation; and generating, by the system, answers for the natural language query based on processing of the third logical representation.

Abstract: A historical log of a plurality of a type of Internet-connected appliances is collected. a dynamic probabilistic graphical model of the time-lined interactions between subsystems and components of the appliances is generated. The probabilistic graphical model is trained by applying machine learning techniques and applying expert knowledge. A natural language processing (NLP) conversational user interface for diagnostic queries regarding operational errors is provided, and responsive to receive a diagnostic query in a conversational format from a user regarding a particular type, make, and model of an appliance of the plurality of the type of Internet-connected appliances, a diagnostic response is provided to the user interface using the natural language processing conversational format.

Abstract: A computer generates a formal planning domain description. The computer receives a first text-based description of a domain in an AI environment. The domain includes an action and an associated attribute, and the description is written in natural language. The computer receives the first text-based description of the domain and extracts a first set of domain actions and associated action attributes. The computer receives audio-visual elements depicting the domain, generates a second text-based description, and extracts a second set of domain actions and associated action attributes. The computer constructs finite state machines corresponding to the extracted actions and attributes. The computer converts the FSMs into a symbolic model, written in a formal planning language, that describes the domain.

Abstract: Tradeoffs, objectives, and one or more machine learning models are analyzed. One or more instantiated machine learning pipelines are generated based on the tradeoffs and objectives. A first instantiated machine learning pipeline is preferred compared to a second instantiated machine learning pipeline based on the plurality of tradeoffs and objectives.

Abstract: Systems, computer-implemented methods, and computer program products to facilitate automated generation of a machine learning pipeline based on a pipeline grammar are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a pipeline structure generator component that generates a machine learning pipeline structure based on a pipeline grammar. The computer executable components can further comprise a pipeline optimizer component that selects one or more machine learning modules that achieve a defined objective to instantiate a machine learning pipeline based on the machine learning pipeline structure.

Abstract: A plurality of objectives is received for a given dataset for an automated machine learning (autoML) process. A set of tradeoffs for the plurality of objectives are received that distribute weights to respective objectives. Pipelines are provided for the dataset that optimize each of the plurality of objectives according to the set of tradeoffs.

Abstract: In an approach for building an automated customer support system, a processor receives a set of sentences extracted from a natural language conversation occurring between an IT support system and a user. A processor extracts an initial state and a goal state from the set of sentences using a Natural Language Classifier. A processor extracts one or more actions from the set of sentences. A processor creates a formal planning model. A processor determines the one or more formal actions are not complete using a first machine learning model. A processor completes the one or more formal actions with one or more missing parts. A processor produces an executable plan using a planner. A processor implements one or more executable scripts according to a sequence of the one or more formal actions of the executable plan using a plan executor.

Abstract: A computer-implemented method for automated policy decision making optimization is disclosed. The computer-implemented method includes creating a dataset from a tabular database, wherein the dataset includes one or more columns selected as state variables, a column selected as action variables, and a column selected as reward variables. The computer-implemented method further includes determining a candidate function approximator Q based on applying at least one state variable, one action variable, and one reward variable to a trained regression model. The computer-implemented method further includes learning a decision policy based on applying the candidate function approximator Q to a reinforcement learning algorithm. The computer-implemented method further includes determining, based on the learned decision policy, an expected reward.

Abstract: In an approach for reasoning with real-valued propositional logic, a processor receives a set of propositional logic formulae, a set of intervals representing upper and lower bounds on truth values of a set of atomic propositions in the set of propositional logic formulae, and a query. A processor generates a logical neural network based on the set of propositional logic formulae and the set of intervals representing upper and lower bounds on truth values. A processor generates a credal network with a same structure of the logical neural network. A processor runs probabilistic inference on the credal network to compute a conditional probability based on the query. A processor outputs the conditional probability as an answer to the query.

Abstract: Embodiments for cause identification in audit data by a processor. A probabilistic logical representation is extracted from text data representing a knowledge domain according to an ontology to identify one or more reoccurring problems of the knowledge domain. A root cause and one or more causal factors of the one or more reoccurring problems is automatically identified using the logical representation such that the identifying associates a confidence level for the root cause and the one or more causal factors.

Abstract: Various embodiments are provided for learning policy explanations in a computing environment by a processor. One or more explanations may be provided that justify validity or invalidity of a claim based on one or more rules extracted from one or more segments of text data of a policy data source using a machine learning operation.