Extending Robust Adversarial Reinforcement Learning Considering Adaptation and Diversity.

Hiroaki Shioya Yusuke Iwasawa Yutaka Matsuo

Published in: ICLR (Workshop) (2018)

Keyphrases

reinforcement learning
multi agent
function approximation
databases
artificial intelligence
multi objective
robust estimation
markov decision processes
optimal policy
computationally efficient
dynamic programming
multiscale
decision trees
learning algorithm
genetic algorithm
information retrieval
neural network