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: Methods and systems for executing confidence-aware reinforcement learning for an Artificial Intelligence (AI) model for subsequent deployment of that AI model in an environment are disclosed. The method includes accessing a set of expert trajectories, each expert trajectory comprising a sequence of expert state-action pairs, the expert entities complying with an expert constraint that is unknown. The method also includes generating a main constraint for the set of expert trajectories, the main constraint being conditioned on a pre-determined confidence level, the pre-determined confidence level being indicative of a probability that the main constraint is at least as constraining as the expert constraint, the main constraint comprising one or more rules limiting the actions that are executable by the AI model, determining a target policy among a plurality of policies, the target policy complying with the main constraint and executing the target policy by the AI model.

Abstract: Methods and processors for inferring constraints for reinforcement learning of an Artificial Intelligence (AI) model for subsequent deployment of that AI model in an environment. The method includes accessing a set of expert trajectories, each expert trajectory comprising a sequence of expert state-action pairs, a given one of the sequences of the expert state-action pairs including information about a given state of the environment and a corresponding action that is to be executed in response to the given state, partitioning the set of expert trajectories into one or more subsets of expert trajectories by employing a trained neural network, each subset being associated with one of the agents and determining, for each agent, an agent constraint based on the corresponding subset of expert trajectories.

Abstract: Methods and systems for federated learning with client clustering are described. A central server conducts rounds of intra-cluster training with two or more clusters to learn, for each cluster, a set of cluster parameters for a respective cluster model. The server merges two clusters into a new merged cluster by communicating, to each client of the two clusters, the cluster parameters of each of the two clusters. The server receives, from each client of the two clusters, performance indicators based on performance of each set of cluster parameters at each client. The central server determines, from the performance indicators, that one of the two clusters should be merged with the other cluster, and defines the new merged cluster to be a union of the two clusters. One set of cluster parameters is selected to be the cluster parameters for the new merged cluster.

Abstract: Servers, methods and systems are disclosed for one-round Bayesian federated learning. Embodiments of the present disclosure may assume that each client produces samples from p(y|x, Di) (i.e. the local predictive posteriors), and combines this information to estimate p(y|x, D) (i.e. the global predictive posterior). In some embodiments, an ensemble method may be used that leverages principled Bayesian techniques to incorporate each client's uncertainty estimates.

Abstract: Methods, systems, and computer-readable media for using inverse reinforcement learning to learn constraints from expert demonstrations are disclosed. The constraints may be learned as a constraint function in two alternating procedures, namely policy optimization and constraint function optimization. Neural network constraint functions may be learned which can represent arbitrary constraints. Embodiments are disclosed that work in all types of environments, with either discrete or continuous state and action spaces. Embodiments are disclosed that may scale to a large set of demonstrations. Embodiments are disclosed that work with any forward CRL technique when finding the optimal policy.

Abstract: A method and machine translation system for bi-directional translation of textual sequences between a first language and a second language are described. The machine translation system includes a first autoencoder configured to receive a vector representation of a first textual sequence in the first language and encode the vector representation of the first textual sequence into a first sentence embedding. The machine translation system also includes a sum-product network (SPN) configured to receive the first sentence embedding and generate a second sentence embedding by maximizing a first conditional probability of the second sentence embedding given the first sentence embedding and a second autoencoder receiving the second sentence embedding, the second autoencoder being trained to decode the second sentence embedding into a vector representation of a second textual sequence in the second language.

Abstract: A method and machine translation system for bi-directional translation of textual sequences between a first language and a second language are described. The machine translation system includes a first autoencoder configured to receive a vector representation of a first textual sequence in the first language and encode the vector representation of the first textual sequence into a first sentence embedding. The machine translation system also includes a sum-product network (SPN) configured to receive the first sentence embedding and generate a second sentence embedding by maximizing a first conditional probability of the second sentence embedding given the first sentence embedding and a second autoencoder receiving the second sentence embedding, the second autoencoder being trained to decode the second sentence embedding into a vector representation of a second textual sequence in the second language.

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 method is provided in an application server, comprising: storing a plurality of primary class definitions in a memory, each primary class definition including a primary class identifier and a plurality of primary class attributes; storing a plurality of secondary class definitions in a memory, each secondary class definition including a secondary class identifier and a plurality of secondary class attributes; receiving a message from a client computing device via a network; based on the content of the message, selecting one of the primary class identifiers, and one of the secondary class identifiers; selecting primary response data corresponding to the selected primary class identifier; selecting secondary response data corresponding to the selected secondary class identifier; generating a response message by combining the primary response data and the secondary response data; and transmitting the response message to the client computing device.

Abstract: A method for detecting a data flow type includes obtaining a header of a first data packet of a current data flow and a pattern vector of the current data flow from the header; comparing the at least one feature dimension in the pattern vector of the current data flow with a corresponding feature dimension in a pattern vector of at least one historical data flow, so as to obtain at least one pattern similarity of the current data flow; predicting a length of the current data flow according to the at least one pattern similarity of the current data flow and a length of the corresponding at least one historical data flow; and comparing the predicted length of the current data flow with a preset threshold, and determining whether the current data flow is a large data flow or a small data flow according to a comparison result.

Abstract: A method for detecting a data flow type includes obtaining a header of a first data packet of a current data flow and a pattern vector of the current data flow from the header; comparing the at least one feature dimension in the pattern vector of the current data flow with a corresponding feature dimension in a pattern vector of at least one historical data flow, so as to obtain at least one pattern similarity of the current data flow; predicting a length of the current data flow according to the at least one pattern similarity of the current data flow and a length of the corresponding at least one historical data flow; and comparing the predicted length of the current data flow with a preset threshold, and determining whether the current data flow is a large data flow or a small data flow according to a comparison result.

Abstract: A method is provided in an application server, comprising: storing a plurality of primary class definitions in a memory, each primary class definition including a primary class identifier and a plurality of primary class attributes; storing a plurality of secondary class definitions in a memory, each secondary class definition including a secondary class identifier and a plurality of secondary class attributes; receiving a message from a client computing device via a network; based on the content of the message, selecting one of the primary class identifiers, and one of the secondary class identifiers; selecting primary response data corresponding to the selected primary class identifier; selecting secondary response data corresponding to the selected secondary class identifier; generating a response message by combining the primary response data and the secondary response data; and transmitting the response message to the client computing device.

Abstract: According to embodiments described in the specification, a method, system and apparatus for configuring a chatbot application are provided. The method includes receiving a plurality of messages from a mobile computing device via a network, and storing the plurality of messages in a memory; identifying a plurality of clusters of related messages among the plurality of messages; presenting the clusters on a display; receiving a selection of one of the clusters, and receiving a class identifier for the selected cluster; retrieving a subset of the related messages corresponding to the selected cluster from the memory; deriving a plurality of attributes defining common characteristics of the subset; and storing the attributes and the class identifier.