Login / Signup
Fast deep reinforcement learning using online adjustments from the past.
Steven Hansen
Pablo Sprechmann
Alexander Pritzel
André Barreto
Charles Blundell
Published in:
CoRR (2018)
Keyphrases
</>
reinforcement learning
multi agent
state space
real time
online learning
function approximation
neural network
real world
deep learning
historical information
balancing exploration and exploitation
decision trees
case study
multi agent systems
supervised learning
online environment