Abstract: Mechanisms are provided for a model-based Reinforcement Learning (RL) computing system. A proprioception module receives a previous state of an environment and a previous action taken by an agent in the environment, and estimates a current state by using a transition model which receives a pair of state and action and produces a next state. The proprioception module modifies an estimate of the transition model so that the modified estimate of the transition model prevents a past invalid action from recurring in a corresponding state, where the past invalid action taken in the corresponding state is one that did not cause a change in state. The proprioception module passes the current state and the modified estimate of the transition model to a model-based RL computer model for generation of a next action to take in the environment.

Abstract: An interoperable workflow management system controls an information disclosing range of a workflow case to prevent transmission delay even when the communication path has a small transmission capacity such that cancellation of the case is guaranteed and the status of processing of the case in its destination can be immediately known. To implement the system, workflow irrelevant data or pointer information indicating the data is selectively transmitted to the destination in accordance with the workflow management system thereof. At cancellation of the case, the irrelevant data is replaced with canceling data. When a request including pointer information for the workflow irrelevant data is received from the destination system, it is assumed that the workflow case is in process.