C
search
search
reviewers
reviewers
feeds
feeds
assignments
assignments
settings
logout
Non-ergodicity in reinforcement learning: robustness via ergodicity transformations.
Dominik Baumann
Erfaun Noorani
James Price
Ole Peters
Colm Connaughton
Thomas B. Schön
Published in:
CoRR (2023)
Keyphrases
</>
reinforcement learning
chaos theory
markov chain
stationary distribution
function approximation
machine learning
queue length
learning algorithm
multi agent
probability distribution
random walk
learning problems
optimal control
transition probabilities
reinforcement learning methods