Login / Signup
Towards High Level Skill Learning: Learn to Return Table Tennis Ball Using Monte-Carlo Based Policy Gradient Method.
Yifeng Zhu
Yongsheng Zhao
Lisen Jin
Jun Wu
Rong Xiong
Published in:
RCAR (2018)
Keyphrases
</>
table tennis
monte carlo
skill learning
gradient method
action space
robot arm
motor skills
markov chain
convergence rate
state space
markov decision processes
real valued
step size
optimal policy
particle filter
temporal difference
reinforcement learning
control law
key features