Improving Generalization with Cross-State Behavior Matching in Deep Reinforcement Learning.

Guan-Ting Liu Guan-Yu Lin Pu-Jen Cheng

Published in: AAMAS (2022)

Keyphrases

reinforcement learning
state space
function approximation
pattern matching
matching algorithm
neural network
machine learning
object recognition
shape matching
behavioral model
video sequences
search space
dynamic programming
supervised learning
markov decision processes