ANALYSIS OF HIERARCHICAL LEARNING WITH REINFORCEMENT FOR THE IMPLEMENTATION OF BEHAVIORAL STRATEGIES OF INTELLIGENT AGENTS

Abstract

The paper discusses the task of evaluating the possibility of using robotic systems (intelligent agents) as a way to solve a problem of monitoring complex infrastructure objects, such as buildings, structures, bridges, roads and other transport infrastructure objects. Methods and algorithms for implementing behavioral strategies of robots, in particular, search algorithms based on decision trees, are examined. The emphasis is placed on the importance of forming the ability of robots to self-learn through reinforcement learning associated with modeling the behavior of living creatures when interacting with unknown elements of the environment. The Q-learning method is considered as one of the types of reinforcement learning that introduces the concept of action value, as well as the approach of “hierarchical reinforcement learning” and its varieties “Options Framework”, “Feudal”, “MaxQ”. The problems of determining such parameters as the value and reward function of agents (mobile robots), as well as the mandatory presence of a subsystem of technical vision, are identified in the segmentation of macro actions. Thus, the implementation of the task of segmentation of macro-actions requires improving the methodological base by applying intelligent algorithms and methods, including deep clustering methods. Improving the effectiveness of hierarchical training with reinforcement when mobile robots operate in conditions of lack of information about the monitoring object is possible by transmitting visual information in a variety of states, which will also increase the portability of experience between them in the future when performing tasks on various objects.