Source
Pattern Recognition and Image Analysis
DATE OF PUBLICATION
10/17/2024
Authors
Alexander Panov
Artem Latyshev
Share
Skill Learning with Empowerment in Reinforcement Learning
Abstract
This paper considers a skill learning method that does not use information about a goal set for an agent. In reinforcement learning, such methods are called intrinsic motivation methods. The proposed algorithm is based on the calculation of the mutual information between the actions of the agent and its states. This approach makes it possible to learn skills that lead to the most uniform reachability of possible states. The skills formed by the algorithm are illustrated by an example of continuous control of the agent’s movement. The usefulness of these skills in solving reinforcement learning problems is analyzed.
Similar publications
You can ask us a question or suggest a joint project in the field of AI
partner@airi.net
For scientific cooperation and
partnership
partnership
pr@airi.net
For journalists and media