PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning.

Alekh Agarwal Mikael Henaff Sham M. Kakade Wen Sun

Published in: CoRR (2020)

Keyphrases

policy gradient
actor critic
reinforcement learning
learning process
policy search
model free reinforcement learning
neural network
policy gradient methods
supervised learning
learning problems
action selection
state action