Login / Signup
Expert Q-learning: Deep Reinforcement Learning with Coarse State Values from Offline Expert Examples.
Li Meng
Anis Yazidi
Morten Goodwin
Paal Engelstad
Published in:
NLDL (2022)
Keyphrases
</>
reinforcement learning
state space
function approximation
multi agent
reinforcement learning algorithms
expert knowledge
real time
cooperative
multi agent systems
optimal policy
model free
domain experts
function approximators
action selection
state variables
attribute values
learning algorithm