Diverse Exploration via Conjugate Policies for Policy Gradient Methods.

Andrew Cohen Xingye Qiao Lei Yu Elliot Way Xiangrong Tong

Published in: AAAI (2019)

Keyphrases

policy gradient methods
natural actor critic
policy gradient
robot arm
actor critic
sufficient conditions
neural network
learning algorithm
reinforcement learning
function approximation
reinforcement learning algorithms
reinforcement learning methods
reinforcement learning problems