C
search
search
reviewers
reviewers
feeds
feeds
assignments
assignments
settings
logout
Approximating gradients for differentiable quality diversity in reinforcement learning.
Bryon Tjanaka
Matthew C. Fontaine
Julian Togelius
Stefanos Nikolaidis
Published in:
GECCO (2022)
Keyphrases
</>
reinforcement learning
high quality
objective function
pairwise
state space
quality assessment
higher quality
data mining
machine learning
dynamic programming
loss function
function approximation
quality measures
model free