The Virtues of Laziness in Model-based RL: A Unified Objective and Algorithms.

Anirudh Vemula Yuda Song Aarti Singh Drew Bagnell Sanjiban Choudhury

Published in: ICML (2023)

Keyphrases

data sets
learning algorithm
orders of magnitude
model free
reinforcement learning
theoretical analysis
data structure
significant improvement
machine learning algorithms
decision trees
multi agent
computational complexity
state space
optimization problems
computational efficiency
times faster