Login / Signup
Utilizing Skipped Frames in Action Repeats for Improving Sample Efficiency in Reinforcement Learning.
Tung Minh Luu
Thanh Nguyen
Thang Vu
Chang D. Yoo
Published in:
IEEE Access (2022)
Keyphrases
</>
reinforcement learning
action selection
learning process
state space
reward shaping
partially observable domains
sample size
frame rate
function approximation
action space
image sequences
spatio temporal
supervised learning
temporal difference
transition model