Interactive Q-Learning Approach for Pick-and-Place Optimization of the Die Attach Process in the Semiconductor Industry

Algorithm 2

Q-tables update algorithm.

Input: , , , ,

Procedure: Initialize every element in , , , with arbitrary numbers

Initialize

Until ( and ordo

Initialize and

Initialize # : current state of the pick agent

Until do

Ifdo# If a strip is full, it is replaced with a new one

# Pick agent update

# Update the current state of the place agent

# Update the feasible action space of the pick agent

# Place agent update

# Select the action of the place agent

# Update the feasible action space of the place agent

Increase by 1

Output: ,