A graph-theoretic approach toward autonomous skill acquisition in reinforcement learning
Sign Up to like & getrecommendations! Published in 2018 at "Evolving Systems"
DOI: 10.1007/s12530-017-9193-9
Abstract: Hierarchical reinforcement learning facilitates learning in large and complex domains by exploiting subtasks and creating hierarchical structures using these subtasks. Subtasks are usually defined through finding subgoals of the problem. Providing mechanisms for autonomous subgoal… read more here.
Keywords: subgoal discovery; skill acquisition; method; reinforcement learning ... See more keywords