Recomposing the Reinforcement Learning Building Blocks with Hypernetworks.

Shai Keynan Elad Sarafian Sarit Kraus

Published in: CoRR (2021)

Keyphrases

building blocks
reinforcement learning
function approximation
reinforcement learning algorithms
state space
multi agent
machine learning

robotic control
back end
optimal policy
temporal difference learning
relational reinforcement learning
decision making
control problems

action selection
learning classifier systems
databases
policy search
multi agent reinforcement learning
robot control
learning algorithm

control system
case study
learning problems
data exchange
multi agent systems
supervised learning
learning process