Abstract: There is provided a computer-implemented method for updating a search distribution of an evolutionary strategies optimizer using an optimizer neural network comprising one or more attention blocks. The method comprises receiving a plurality of candidate solutions, one or more parameters defining the search distribution that the plurality of candidate solutions are sampled from, and fitness score data indicating a fitness of each respective candidate solution of the plurality of candidate solutions. The method further comprises processing, by the one or more attention neural network blocks, the fitness score data using an attention mechanism to generate respective recombination weights corresponding to each respective candidate solution. The method further comprises updating the one or more parameters defining the search distribution based upon the recombination weights applied to the plurality of candidate solutions.

Abstract: In one aspect there is provided a method for training a neural network system by reinforcement learning. The neural network system may be configured to receive an input observation characterizing a state of an environment interacted with by an agent and to select and output an action in accordance with a policy aiming to satisfy an objective. The method may comprise obtaining a policy set comprising one or more policies for satisfying the objective and determining a new policy based on the one or more policies. The determining may include one or more optimization steps that aim to maximize a diversity of the new policy relative to the policy set under the condition that the new policy satisfies a minimum performance criterion based on an expected return that would be obtained by following the new policy.

Abstract: A reinforcement learning system, method, and computer program code for controlling an agent to perform a plurality of tasks while interacting with an environment. The system learns options, where an option comprises a sequence of primitive actions performed by the agent under control of an option policy neural network. In implementations the system discovers options which are useful for multiple different tasks by meta-learning rewards for training the option policy neural network whilst the agent is interacting with the environment.

Abstract: A multi-modal computer classification network system for use in classifying data records is described herein. The system includes a memory device, a first classification computer server, a second classification computer server, and a policy computer server. The memory device includes an item records database and a labeling database. The first classification computer server includes a first classifier program that is configured to select an item record from the item database and generate a first classification record including a first ranked list of class labels. The second classification computer server includes a second classifier program that is configured to generate a second classification record including a second ranked list of class labels. The policy computer server includes a policy network that is programmed to determine a predicted class label based on the first and second ranked lists of class labels.

Abstract: A multi-modal computer classification network system for use in classifying data records is described herein. The system includes a memory device, a first classification computer server, a second classification computer server, and a policy computer server. The memory device includes an item records database and a labeling database. The first classification computer server includes a first classifier program that is configured to select an item record from the item database and generate a first classification record including a first ranked list of class labels. The second classification computer server includes a second classifier program that is configured to generate a second classification record including a second ranked list of class labels. The policy computer server includes a policy network that is programmed to determine a predicted class label based on the first and second ranked lists of class labels.