Login / Signup
EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL.
Seyed Kamyar Seyed Ghasemipour
Dale Schuurmans
Shixiang Shane Gu
Published in:
CoRR (2020)
Keyphrases
</>
transfer learning
reinforcement learning
learning algorithm
active learning
function approximation
model free
real time
online learning
reinforcement learning algorithms
multi agent
state space
neural network
genetic algorithm
optimal policy
state action