Abstract: There is described a machine learning system comprising a first subsystem and a second subsystem remote from the first subsystem. The first subsystem comprises an environment having multiple possible states and a decision making subsystem comprising one or more agents. Each agent is arranged to receive state information indicative of a current state of the environment and to generate an action signal dependent on the received state information and a policy associated with that agent, the action signal being operable to cause a change in a state of the environment. Each agent is further arranged to generate experience data dependent on the received state information and information conveyed by the action signal. The first subsystem includes a first network interface configured to send said experience data to the second subsystem and to receive policy data from the second subsystem.

Abstract: Method in monitoring the condition of machines, in which method measurements are performed on a number of machines or machine parts to obtain quantities descriptive of the condition of the machines. In the method, characteristics or symptoms related to the operation or condition of the machine are derived from the measured quantities, a characteristic vector describing the current operational state of the machine is generated from the characteristics, characteristic vector categories are formed from characteristic vectors describing the same operational state, and a database is created in which are stored characteristic vector categories describing different operational states of the machines.