FPGA Acceleration of ROS2-Based Reinforcement Learning Agents.

Daniel Pinheiro Leal Midori Sugaya Hideharu Amano Takeshi Ohkawa

Published in: CANDAR (Workshops) (2020)

Keyphrases

reinforcement learning agents
dynamic environments
reinforcement learning
state abstraction
hardware implementation
field programmable gate array
multi agent
multi agent environments
learning algorithm
machine learning
transfer learning
data sets
data mining
information retrieval
path planning