Distributional Reinforcement Learning for Efficient Exploration.

Borislav Mavrin Hengshuai Yao Linglong Kong Kaiwen Wu Yaoliang Yu

Published in: ICML (2019)

Keyphrases

reinforcement learning
function approximation
state space
co occurrence
reinforcement learning algorithms
model free
markov decision processes

learning process
direct policy search
policy search
multi agent reinforcement learning
temporal difference learning
control problems
optimal policy

multi agent
temporal difference
multiscale
continuous state
learning algorithm
robotic control
transfer learning

action selection
dynamic programming
function approximators
evolutionary learning
artificial intelligence
data sets