A unified strategy for implementing curiosity and empowerment driven reinforcement learning.

Ildefons Magrans de Abril Ryota Kanai

Published in: CoRR (2018)

Keyphrases

reinforcement learning
data driven
function approximation
decision making
multi agent
search algorithm
unified model
neural network
learning algorithm
information systems
case study
bayesian networks
dynamic programming
optimal policy
markov decision processes
action selection