Value-Based Continuous Control Without Concrete State-Action Value Function.

Jin Zhu Haixian Zhang Zhen Pan

Published in: ICSI (2) (2021)

Keyphrases

state action
action space
reinforcement learning
evaluation function
state space
state transitions
function approximators
markov decision process
control system
control strategy
action selection
kernel matrix
average reward
belief state
learning algorithm
function approximation
decision making