Precise Evaluation for Continuous Action Control in Reinforcement Learning.

Fengkai Ke Daxing Zhao Guodong Sun Wei Feng

Published in: HPCCT/BDAI (2019)

Keyphrases

reinforcement learning
policy search
continuous action
continuous state
control problems
robot control
optimal control
control strategies
control system
state space
function approximation
control strategy
optimal policy
markov decision processes
robotic systems
finite state
control policy
neural network