International Business Machines Corporation
Artificially intelligent interaction agent

Abstract:

A system includes a memory having instructions therein and at least one processor configured to execute the instructions to: begin control of a user-interaction session; determine a first user state; use a reinforcement learning agent to select a first motivational action; communicate the first motivational action to a user device; determine a second user state; generate a reward based at least in part on a tiered reinforcement learning reward categorization of the second user state; communicate the reward and the second user state to the reinforcement learning agent; update the reinforcement learning agent; and determine, based at least in part on whether the second user state corresponds to a goal of the user-interaction session, to wind up control of the user-interaction session.