Login / Signup
Theoretical Analysis of Efficiency and Robustness of Softmax and Gap-Increasing Operators in Reinforcement Learning.
Tadashi Kozuno
Eiji Uchibe
Kenji Doya
Published in:
AISTATS (2019)
Keyphrases
</>
theoretical analysis
reinforcement learning
computational efficiency
numerical simulations
temporal difference learning
function approximation
high robustness
information retrieval
case study
least squares
data mining
multi agent
markov decision processes
high efficiency