Abstract: Disclosed implementations relate to automating semantically-similar computing tasks across multiple contexts. In various implementations, an initial natural language input and a first plurality of actions performed using a first computer application may be used to generate a first task embedding and a first action embedding in action embedding space. An association between the first task embedding and first action embedding may be stored. Later, subsequent natural language input may be used to generate a second task embedding that is then matched to the first task embedding. Based on the stored association, the first action embedding may be identified and processed using a selected domain model to select actions to be performed using a second computer application. The selected domain model may be trained to translate between an action space of the second computer application and the action embedding space.

Abstract: This specification is generally directed to techniques for robust natural language (NL) based control of computer applications. In many implementations, the NL control is at least selectively interactive in that the user feedback input is solicited, and received, in resolving action(s), resolving action set(s), generating domain specific knowledge, and/or in providing feedback on implemented action set(s). The user feedback input can be utilized in further training of machine learning model(s) utilized in the NL based control of the computer applications.

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: Disclosed implementations relate to automating semantically-similar computing tasks across multiple contexts. In various implementations, an initial natural language input and a first plurality of actions performed using a first computer application may be used to generate a first task embedding and a first action embedding in action embedding space. An association between the first task embedding and first action embedding may be stored. Later, subsequent natural language input may be used to generate a second task embedding that is then matched to the first task embedding. Based on the stored association, the first action embedding may be identified and processed using a selected domain model to select actions to be performed using a second computer application. The selected domain model may be trained to translate between an action space of the second computer application and the action embedding space.

Abstract: Implementations are directed to improving network anti-fragility. In some aspects, a method includes receiving parameter data from a network of nodes, the parameter data comprising attributes, policies, and action spaces for each node in the network of nodes; configuring one or more interruptive events on one or more nodes included in the network of nodes; determining a first action of each node in the network of nodes in response to the one or more interruptive events; determining a first performance metric, for each node, that corresponds to the first action, wherein the first performance matric is determined based on at least a first reward value associated with the first action; continuously updating the first action in an iterative process to obtain a final action, wherein a performance metric corresponding to the final action satisfies a performance threshold, and transmitting the final action for each node to the network of nodes.

Abstract: Methods and systems including receiving a plurality of shipping bids from a plurality of shipping entities, each entity having goods to ship from locations to destinations, wherein each bid represents an option to ship goods at a shipping price, and wherein each bid comprises a plurality of shipping parameters; receiving a plurality of carrier bids from a plurality of carrier entities, each entity transporting the goods, wherein each bid represents an option to transport the goods at a price, and wherein each bid comprises a plurality of carrier parameters; performing a matching process to generate a plurality of pair-wise partial matches, wherein each match associates a shipping and carrier bid at a modified price, wherein the modified price is based on a deviation between the parameters; providing information representing the matches to the shipping and carrier entities; and generating training data representing which matches were exercised.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automatic generation of a supply chain simulation. The methods, systems, and apparatus include actions of obtaining supply chain data of a supply chain, generating a supply chain network graph that represents relationships between locations indicated by the supply chain data, determining classifications of the locations indicated by the supply chain data, determining agent rule models based on the supply chain data, and generating a supply chain simulation based on the supply chain network graph, the classifications of the locations, and the agent rule models.

Abstract: Implementations are described herein for formulating natural language descriptions based on temporal sequences of digital images. In various implementations, a natural language input may be analyzed. Based on the analysis, a semantic scope to be imposed on a natural language description that is to be formulated based on a temporal sequence of digital images may be determined. The temporal sequence of digital images may be processed based on one or more machine learning models to identify one or more candidate features that fall within the semantic scope. One or more other features that fall outside of the semantic scope may be disregarded. The natural language description may be formulated to describe one or more of the candidate features.

Abstract: Systems and methods for managing chemical recycling processes include accessing characterization data of a feedstock, the characterization data comprising one or more spectra collected according to one or more spectroscopic methods. The methods include predicting, using the characterization data, a set of constituent materials included in the feedstock. The methods include predicting a material composition of the feedstock using the predicted set of constituent materials. The methods include identifying, at least in part using the predicted material composition of the feedstock, one or more target products. The methods include generating a set of chemical reaction schemas enabling a conversion of at least part of the feedstock into the one or more target products. The methods also include storing identifications of the material composition of the feedstock, the one or more target products, and the set of chemical reaction schemas in a data store.