Login / Signup
Ajustando Q-Learning para Generar Jugadores Automáticos: un Ejemplo Basado en Atari Breakout.
Guillermo Fernández-Vizcaíno
Francisco José Gallego-Durán
Published in:
CoSECivi (2016)
Keyphrases
</>
reinforcement learning
function approximation
multi agent
cooperative
state space
model free
learning algorithm
action selection
learning rate
temporal difference learning
reinforcement learning algorithms
optimal policy
dynamic programming
real valued
learning tasks
policy iteration
learning agent