Login / Signup
MazeCov-Q: An Efficient Maze-Based Reinforcement Learning Accelerator for Coverage.
Infall Syafalni
Mohamad Imam Firdaus
Andi M. Riyadhus Ilmy
Nana Sutisna
Trio Adiono
Published in:
COOL CHIPS (2023)
Keyphrases
</>
reinforcement learning
function approximation
multi agent
computationally efficient
real time
information systems
optimal control
model free
action selection
image processing
dynamic programming
state space
markov decision process
robotic control