ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning, & Snapshot Ensembling.

Christopher Schulze Marcus Schulze

Published in: CoRR (2018)

Keyphrases

reinforcement learning
learning algorithm
cooperative
function approximation
reinforcement learning algorithms
multi agent
state space
user experience
predictive accuracy
information systems
genetic algorithm
dynamic programming
model free
stochastic approximation