Scaling Up Q-Learning via Exploiting State–Action Equivalence
Sign Up to like & getrecommendations! Published in 2023 at "Entropy"
DOI: 10.3390/e25040584
Abstract: Recent success stories in reinforcement learning have demonstrated that leveraging structural properties of the underlying environment is key in devising viable methods capable of solving complex tasks. We study off-policy learning in discounted reinforcement learning,… read more here.
Keywords: scaling learning; structure; equivalence structure; equivalence ... See more keywords