Abstract: As opposed to a rigid approach, implementations disclosed herein utilize a flexible approach in automatically determining an action set to utilize in attempting performance of a task that is requested by natural language input of a user. The approach is flexible at least in that embedding technique(s) and/or action model(s), that are utilized in generating action set(s) from which the action set to utilize is determined, are at least selectively varied. Put another way, implementations leverage a framework via which different embedding technique(s) and/or different action model(s) can at least selectively be utilized in generating different candidate action sets for given NL input of a user. Further, one of those action sets can be selected for actual use in attempting real-world performance of a given task reflected by the given NL input. The selection can be based on a suitability metric for the selected action set and/or other considerations.

Abstract: Computer-implemented methods may include accessing a predictive function. The predictive function may be configured to receive a partial or complete bond string and position (BSP) representation of a molecule of a reactant ionic liquid, where the representation identifies relative positions of atoms in the molecule. The predictive function may be configured to predict a reaction-characteristic value that characterizes a reaction between the ionic liquid and a particular polymer. The predictive function may be generated using training data corresponding to a set of molecules that were selected using Bayesian optimization, one or more previous versions of the predictive function, and experimentally derived reaction-characteristic values characterizing reactions between the molecules and the particular polymer. The method may also include identifying a particular ionic liquid as a prospect for depolymerizing the particular polymer based on the predictive function.

Abstract: Computer-implemented methods may include accessing a multi-dimensional embedding space that supports relating embeddings of molecules to predicted values of a given property of the molecules. The method may also include identifying one or more points of interest within the embedding space based on the predicted values. Each of the one or more points of interest may include a set of coordinate values within the multi-dimensional embedding space and may be associated with a corresponding predicted value of the given property. The method may further include generating, for each of the one or more points of interest, a structural representation of a molecule by transforming the set of coordinate values included in the point of interest using a decoder network. The method may include outputting a result that identifies, for each of the one or more points of interest, the structural representation of the molecule corresponding to the point of interest.