Abstract: The present invention generally relates to a modular high power bi-directional half bridge buck/boost converter assembly and, in particular, to a system for converting power from one form of current (either AC or DC) to a differing level of voltage, either lower (buck) or higher (boost), to output a wave signal based on pulse wave modulation (PWM) switching control by means of an external digital controller and methods of operation. In particular, an inverter-converter system includes at least one half bridge module including a plurality of circuit components, at least one inductor which is connected to the at least one half bridge module and a power supply, and a controller which is configured to receive and send instructions to the at least one half bridge module for converting an input voltage to an output voltage and dynamically tune switching frequencies based on a load of the inverter-converter system.

Abstract: A rotary electric machine arranged as a brushless electric ring motor is described and includes a rotor that is disposed within a stator and arranged to rotate on a guide element. The rotor has a plurality of ferritic elements arranged on an outer surface, and the stator is an annular device having a plurality of electro-magnetic elements arranged on an inner portion between first and second flanges. The first and second flanges both include an annular ring that is fabricated from a non-magnetic material and has a plurality of ferromagnetic elements. The ferromagnetic elements are magnetically coupled to corresponding ones of the electro-magnetic elements to exert magnetic force on the ferritic elements of the rotor when the electro-magnetic elements are activated. The rotary electric machine may operate as a first thrust generating system that is upstream of a second thrust generating system for a turbojet engine.

Abstract: The present invention generally relates to a modular high power bi-directional half bridge buck/boost converter assembly and, in particular, to a system for converting power from one form of current (either AC or DC) to a differing level of voltage, either lower (buck) or higher (boost), to output a wave signal based on pulse wave modulation (PWM) switching control by means of an external digital controller and methods of operation. In particular, an inverter-converter system includes at least one half bridge module including a plurality of circuit components, at least one inductor which is connected to the at least one half bridge module and a power supply, and a controller which is configured to receive and send instructions to the at least one half bridge module for converting an input voltage to an output voltage and dynamically tune switching frequencies based on a load of the inverter-converter system.

Abstract: Certain aspects of the present disclosure provide techniques for an aerodynamic surface actuation system, including: a middle track connected to an aerodynamic surface and configured to move along a plurality of intermediate tracks, wherein one or more inner surfaces of the middle track are configured to interface with one or more outer surfaces of the plurality of intermediate tracks; a plurality of outer tracks, each including a flange and configured to interface with one or more inner surfaces of the plurality of intermediate tracks; and an actuator configured to control a position of the middle track and a position of the plurality of intermediate tracks via a plurality of linkages.

Abstract: Disclosed are systems, methods, and devices for generating a visualization of a deep reinforcement learning (DRL) process. State data is received, reflective of states of an environment explored by an DRL agent, each state corresponding to a time step. For each given state, saliency metrics are calculated by processing the state data, each metric measuring saliency of a feature at the time step corresponding to the given state. A graphical visualization is generated, having at least two dimensions in which: each feature of the environment is graphically represented along a first axis; and each time step is represented along a second axis; and a plurality of graphical markers representing corresponding saliency metrics, each graphical marker having a size commensurate with the magnitude of the particular saliency metric represented, and a location along the first and second axes corresponding to the feature and time step for the particular saliency metric.

Abstract: A computer system and method for extending parallelized asynchronous reinforcement learning for training a neural network is described in various embodiments, through coordinated operation of plurality of hardware processors or threads such that each functions as a worker agent that is configured to simultaneously interact with a target computing environment for local gradient computation based on a loss determination and to update global network parameters based at least on local gradient computation to train the neural network through modifications of weighted interconnections between interconnected computing units as gradient computation is conducted across a plurality of iterations of a target computing environment, the loss determination including at least a policy loss term (actor), a value loss term (critic), and an auxiliary control loss. Variations are described further where the neural network is adapted to include terminal state prediction and action guidance.

Abstract: Certain aspects of the present disclosure provide techniques for an aerodynamic surface actuation system, including: a middle track connected to an aerodynamic surface and configured to move along a plurality of intermediate tracks, wherein one or more inner surfaces of the middle track are configured to interface with one or more outer surfaces of the plurality of intermediate tracks; a plurality of outer tracks, each including a flange and configured to interface with one or more inner surfaces of the plurality of intermediate tracks; and an actuator configured to control a position of the middle track and a position of the plurality of intermediate tracks via a plurality of linkages.

Abstract: A tie-rod with a swivel tie-rod end includes a tie-rod central rod and a first tie-rod end including a swivel joint. The first tie-rod end is connected to the tie-rod central rod by the swivel joint. The swivel joint is operable to enable rotation of the first tie-rod end with respect to the tie-rod central rod while maintaining a common longitudinal axis between the first tie-rod end and the tie-rod central rod. The tie-rod further includes a second tie-rod end connected to the tie-rod central rod.

Abstract: A rotary electric machine arranged as a brushless electric ring motor is described and includes a rotor that is disposed within a stator and arranged to rotate on a guide element. The rotor has a plurality of ferritic elements arranged on an outer surface, and the stator is an annular device having a plurality of electro-magnetic elements arranged on an inner portion between first and second flanges. The first and second flanges both include an annular ring that is fabricated from a non-magnetic material and has a plurality of ferromagnetic elements. The ferromagnetic elements are magnetically coupled to corresponding ones of the electro-magnetic elements to exert magnetic force on the ferritic elements of the rotor when the electro-magnetic elements are activated. The rotary electric machine may operate as a first thrust generating system that is upstream of a second thrust generating system for a turbojet engine.

Abstract: Systems, methods, and computer readable media directed to interactive reinforcement learning with dynamic reuse of prior knowledge are described in various embodiments. The interactive reinforcement learning is adapted for providing computer implemented systems for dynamic action selection based on confidence levels associated with demonstrator data or portions thereof.

Abstract: A computer system and method for extending parallelized asynchronous reinforcement learning to include agent modeling for training a neural network is described. Coordinated operation of plurality of hardware processors or threads is utilized such that each functions as a worker process that is configured to simultaneously interact with a target computing environment for local gradient computation based on a loss determination mechanism and to update global network parameters. The loss determination mechanism includes at least a policy loss term (actor), a value loss term (critic), and a supervised cross entropy loss. Variations are described further where the neural network is adapted to include a latent space to track agent policy features.

Abstract: Systems are methods are provided for facilitating explainability of decision-making by reinforcement learning agents. A reinforcement learning agent is instantiated which generates, via a function approximation representation, learned outputs governing its decision-making. Data records of a plurality of past inputs for the agent are stored, each of the past inputs including values of a plurality of state variables. Data records of a plurality of past learned outputs of the agent are also stored. A group definition data structure defining groups of the state variables are received. For a given past input a given group, data generated reflective of a perturbed input by altering a value of at least one state variable is generated, and are presented to the reinforcement learning agent to obtain a perturbed learned output generated by the reinforcement learning agent; and a distance metric is generated reflective of a magnitude of difference between the perturbed learned output and the past learned output.

Abstract: Disclosed are systems, methods, and devices for training a learning agent. A learning agent that maintains a reinforcement learning neural network is instantiated. State data reflective of a state of an environment explored by the learning agent is received. An uncertainty metric calculated upon processing the state data, the uncertainty metric measuring epistemic uncertainty of the learning agent. Upon determining that the uncertainty metric exceeds a pre-defined threshold: a request signal requesting an action suggestion from a demonstrator is sent; a suggestion signal reflective of the action suggestion is received; and an action signal to implement the action suggestion is sent.

Abstract: Disclosed are systems, methods, and devices for generating a visualization of a deep reinforcement learning (DRL) process. State data is received, reflective of states of an environment explored by an DRL agent, each state corresponding to a time step. For each given state, saliency metrics are calculated by processing the state data, each metric measuring saliency of a feature at the time step corresponding to the given state. A graphical visualization is generated, having at least two dimensions in which: each feature of the environment is graphically represented along a first axis; and each time step is represented along a second axis; and a plurality of graphical markers representing corresponding saliency metrics, each graphical marker having a size commensurate with the magnitude of the particular saliency metric represented, and a location along the first and second axes corresponding to the feature and time step for the particular saliency metric.

Abstract: A gas production line including: an inlet; an outlet; and a wet gas condenser connected between the inlet and the outlet, wherein the wet gas condenser includes: a condensing chamber; a condensing surface; and a collecting chamber, wherein, in use, water vapour in wet gas passing over the condensing surface is condensed into liquid water, the liquid water flowing along a predetermined flow path into the collecting chamber.

Abstract: A system for a machine reinforcement learning architecture for an environment with a plurality of agents includes: at least one memory and at least one processor configured to provide a multi-agent reinforcement learning architecture, the multi-agent reinforcement learning model based on a mean field Q function including multiple types of agents, wherein each type of agent has a corresponding mean field.

Abstract: A computer system and method for extending parallelized asynchronous reinforcement learning to include agent modeling for training a neural network is described. Coordinated operation of plurality of hardware processors or threads is utilized such that each functions as a worker process that is configured to simultaneously interact with a target computing environment for local gradient computation based on a loss determination mechanism and to update global network parameters. The loss determination mechanism includes at least a policy loss term (actor), a value loss term (critic), and a supervised cross entropy loss. Variations are described further where the neural network is adapted to include a latent space to track agent policy features.

Abstract: A computer system and method for extending parallelized asynchronous reinforcement learning for training a neural network is described in various embodiments, through coordinated operation of plurality of hardware processors or threads such that each functions as a worker agent that is configured to simultaneously interact with a target computing environment for local gradient computation based on a loss determination and to update global network parameters based at least on local gradient computation to train the neural network through modifications of weighted interconnections between interconnected computing units as gradient computation is conducted across a plurality of iterations of a target computing environment, the loss determination including at least a policy loss term (actor), a value loss term (critic), and an auxiliary control loss. Variations are described further where the neural network is adapted to include terminal state prediction and action guidance.

Abstract: Systems, methods, and computer readable media directed to interactive reinforcement learning with dynamic reuse of prior knowledge are described in various embodiments. The interactive reinforcement learning is adapted for providing computer implemented systems for dynamic action selection based on confidence levels associated with demonstrator data or portions thereof.

Abstract: Disclosed herein are a system and method for providing a machine learning architecture based on monitored demonstrations. The system may include: a non-transitory computer-readable memory storage; at least one processor configured for dynamically training a machine learning architecture for performing one or more sequential tasks, the at least one processor configured to provide: a data receiver for receiving one or more demonstrator data sets, each demonstrator data set including a data structure representing the one or more state-action pairs; a neural network of the machine learning architecture, the neural network including a group of nodes in one or more layers; and a pre-training engine configured for processing the one or more demonstrator data sets to extract one or more features, the extracted one or more features used to pre-train the neural network based on the one or more state-action pairs observed in one or more interactions with the environment.