Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an industrial plant controller that controls operation of an industrial plant. In one aspect, a method comprises generating training data using an industrial plant simulation model that simulates operation of the industrial plant. The industrial plant controller is trained by a reinforcement learning technique using the training data. The industrial plant controller is configured to process an input comprising a state vector characterizing a state of the industrial plant in accordance with a plurality of industrial plant controller parameters to generate an action selection policy output that defines a control action to be performed to control the operation of the industrial plant.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an industrial plant controller that controls operation of an industrial plant. In one aspect, a method comprises generating training data using an industrial plant simulation model that simulates operation of the industrial plant. The industrial plant controller is trained by a reinforcement learning technique using the training data. The industrial plant controller is configured to process an input comprising a state vector characterizing a state of the industrial plant in accordance with a plurality of industrial plant controller parameters to generate an action selection policy output that defines a control action to be performed to control the operation of the industrial plant.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an industrial plant controller that controls operation of an industrial plant. In one aspect, a method comprises generating training data using an industrial plant simulation model that simulates operation of the industrial plant. The industrial plant controller is trained by a reinforcement learning technique using the training data. The industrial plant controller is configured to process an input comprising a state vector characterizing a state of the industrial plant in accordance with a plurality of industrial plant controller parameters to generate an action selection policy output that defines a control action to be performed to control the operation of the industrial plant.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an industrial plant controller that controls operation of an industrial plant. In one aspect, a method comprises generating training data using an industrial plant simulation model that simulates operation of the industrial plant. The industrial plant controller is trained by a reinforcement learning technique using the training data. The industrial plant controller is configured to process an input comprising a state vector characterizing a state of the industrial plant in accordance with a plurality of industrial plant controller parameters to generate an action selection policy output that defines a control action to be performed to control the operation of the industrial plant.

Abstract: Method of preparing foamed solid aminoformaldehyde furfurylalcohol products by polymerizing a liquid furfurylalcohol containing aminoformaldehyde resin composition in the presence of an acid, characterized in using as a starting material a resin compositioncontaining 15-90% by weight of total free and bound furfurylalcohol and having an urea:formaldehyde molar ratio of 1:1 to 1:5 and at least 10 parts by weight of a boron compound per 100 parts by weight of said resin, the boron compound being present in an amount sufficient so that the foam product will pass the muffle furnace test at 500.degree. C., and has no second exotherm at 200.degree. C. The boron compound can be selected from the group consisting of boric acid, boron oxide, borax, boric acid esters, boron tribromide, boron trichloride, boron nitride, boron phosphate, boron trifluoride etherate, boron trifluoride methanol, boron trifloride monoethylamine, complexes of boric acid with polyhydroxyl compounds, and mixtures thereof.

Abstract: A synthetic foam and a process for its preparation is disclosed comprising (a) a polymerized mass of at least 50 parts by weight of furfuryl alcohol, at least one part by weight of at least one amino compound selected from the group consisting of urea, thiourea and melamine, and up to 49 parts by weight formaldehyde, and (b) an equal or less amount of filler.

Abstract: A synthetic foam and a process for its preparation is disclosed comprising (a) a polymerized mass of at least 50 parts by weight of furfuryl alcohol, at least one part by weight of at least one amino compound selected from the group consisting of urea, thiourea and melamine, and up to 49 parts by weight formaldehyde, and (b) an equal or less amount of filler.