Abstract: A generative cooperative network (GCN) comprises a dataset generator model and a learner model. The dataset generator model generates training datasets used to train the learner model. The trained learner model is evaluated according to a reference training dataset. The dataset generator model is modified according to the evaluation. The training datasets, the dataset generator model, and the leaner model are stored by the GCN. The trained learner model is configured to receive input and to generate output based on the input.

Abstract: A self-driving vehicle implements a deep reinforcement learning based model. The self-driving vehicle comprise one or more sensors configured to capture sensor data of an environment of the self-driving vehicle, a control system configured to navigate the self-driving vehicle, and a controller to determine and provide instructions to the control system. The controller implements a deep reinforcement learning based model that inputs the sensor data captured by the sensors to determine actions to perform by the control system. The model includes an archive storing states reachable by an agent in a training environment, each state stored in the archive is associated with a trajectory for reaching the state. The archive is generated by visiting states stored in the archive and performing actions to explore and find new states. New states are stored in the archive with their trajectories.

Abstract: Systems and methods are disclosed herein for selecting a parameter vector from a set of parameter vectors for a neural network and generating a plurality of copies of the parameter vector. The systems and methods generate a plurality of modified parameter vectors by perturbing each copy of the parameter vector with a different perturbation seed, and determine, for each respective modified parameter vector, a respective measure of novelty. The systems and methods determine an optimal new parameter vector based on each respective measure of novelty for each respective one of the plurality of modified parameter vectors, and determine behavior characteristics of the new parameter vector. The systems and methods store the behavior characteristics of the new parameter vector in an archive.

Abstract: A system uses neural networks for applications such as navigation of autonomous vehicles or mobile robots. The system uses a trained neural network model that comprises fixed parameters that remain unchanged during execution of the model, plastic parameters that are modified during execution of the model, and nodes that generate outputs based on the inputs, fixed parameters, and the plastic parameters. The system provides input data to the neural network model and executes the neural network model. The system updates the plastic parameters of the neural network model by adjusting the rate at which the plastic parameters update over time based on at least one output of a node.

Abstract: A generative cooperative network (GCN) comprises a dataset generator model and a learner model. The dataset generator model generates training datasets used to train the learner model. The trained learner model is evaluated according to a reference training dataset. The dataset generator model is modified according to the evaluation. The training datasets, the dataset generator model, and the leaner model are stored by the GCN. The trained learner model is configured to receive input and to generate output based on the input.

Abstract: Systems and methods are disclosed herein for ensuring a safe mutation of a neural network. A processor determines a threshold value representing a limit on an amount of divergence of response for the neural network. The processor identifies a set of weights for the neural network, the set of weights beginning as an initial set of weights. The processor trains the neural network by repeating steps including determining a safe mutation representing a perturbation that results in a response of the neural network that is within the threshold divergence, and modifying the set of weights of the neural network in accordance with the safe mutation.

Abstract: A self-driving vehicle implements a deep reinforcement learning based model. The self-driving vehicle comprise one or more sensors configured to capture sensor data of an environment of the self-driving vehicle, a control system configured to navigate the self-driving vehicle, and a controller to determine and provide instructions to the control system. The controller implements a deep reinforcement learning based model that inputs the sensor data captured by the sensors to determine actions to perform by the control system. The model includes an archive storing states reachable by an agent in a training environment, each state stored in the archive is associated with a trajectory for reaching the state. The archive is generated by visiting states stored in the archive and performing actions to explore and find new states. New states are stored in the archive with their trajectories.

Abstract: Systems and methods are disclosed herein for training neural networks that can be adapted to new inputs, new tasks, new environment, etc. by re-training them efficiently. A parameter vector is initialized for a neural network. Perturbed parameter vectors are determined using the parameter vector. Behavior characteristics are determined for each perturbed parameter vector. The parameter vector is modified by moving it in the parameter vector space in a direction that maximizes a diversity metric. Other neural networks can be trained for new tasks or new environments using the parameter vector of the neural network.

Abstract: A source system initializes, using an initialization seed, a first parameter vector representing weights of a neural network. The source system determines a second parameter vector by performing a sequence of mutations on the first parameter vector, the mutations each being based on a perturbation seed. The source system generates, and stores to memory, an encoded representation of the second parameter vector that comprises the initialization seed and a sequence of perturbation seeds corresponding to the sequence of mutations. The source system transmits the data structure to a target system, which processes a neural network based on the data structure.

Abstract: Systems and methods are disclosed herein for ensuring a safe mutation of a neural network. A processor determines a threshold value representing a limit on an amount of divergence of response for the neural network. The processor identifies a set of weights for the neural network, the set of weights beginning as an initial set of weights. The processor trains the neural network by repeating steps including determining a safe mutation representing a perturbation that results in a response of the neural network that is within the threshold divergence, and modifying the set of weights of the neural network in accordance with the safe mutation.

Abstract: Systems and methods are disclosed herein for selecting a parameter vector from a set of parameter vectors for a neural network and generating a plurality of copies of the parameter vector. The systems and methods generate a plurality of modified parameter vectors by perturbing each copy of the parameter vector with a different perturbation seed, and determine, for each respective modified parameter vector, a respective measure of novelty. The systems and methods determine an optimal new parameter vector based on each respective measure of novelty for each respective one of the plurality of modified parameter vectors, and determine behavior characteristics of the new parameter vector. The systems and methods store the behavior characteristics of the new parameter vector in an archive.

Abstract: A source system initializes, using an initialization seed, a first parameter vector representing weights of a neural network. The source system determines a second parameter vector by performing a sequence of mutations on the first parameter vector, the mutations each being based on a perturbation seed. The source system generates, and stores to memory, an encoded representation of the second parameter vector that comprises the initialization seed and a sequence of perturbation seeds corresponding to the sequence of mutations. The source system transmits the data structure to a target system, which processes a neural network based on the data structure.