Login / Signup
A Novel Reinforcement Learning Sampling Method Without Additional Environment Feedback in Hindsight Experience Replay.
Chenxing Li
Yinlong Liu
Zhenshan Bing
Jan Seyler
Shahram Eivazi
Published in:
RiTA (2021)
Keyphrases
</>
reinforcement learning
real time
state space
robocup soccer
multi agent environments
machine learning
reward signal
exploration strategy
model free
dynamic environments
mobile robot
multi agent
learning algorithm
markov decision processes
function approximation
optimal control
sensory inputs
search engine