Optimistic Temporal Difference Learning for 2048.

Hung Guei Lung-Pin Chen I-Chen Wu

Published in: IEEE Trans. Games (2022)

Keyphrases

temporal difference learning
function approximation
fixed point
evaluation function
game playing
reinforcement learning
approximate value iteration
temporal difference
reinforcement learning algorithms
monte carlo
markov decision process
markov decision processes
policy iteration
dynamic programming
model free