Login / Signup
Efficient Model-Based Concave Utility Reinforcement Learning through Greedy Mirror Descent.
Bianca Marin Moreno
Margaux Brégère
Pierre Gaillard
Nadia Oudjane
Published in:
AISTATS (2024)
Keyphrases
</>
reinforcement learning
model free
objective function
greedy algorithm
computationally expensive
function approximation
dynamic programming
data driven
cost effective
temporal difference
real time
markov decision processes
utility function
search algorithm
data structure
multi agent
learning algorithm
data sets