State-Separated SARSA: A Practical Sequential Decision-Making Algorithm with Recovering Rewards.

Yuto Tanimoto Kenji Fukumizu

Published in: CoRR (2024)

Keyphrases

optimization algorithm
np hard
learning algorithm
cost function
neural network
optimal solution
computational complexity
particle swarm optimization
machine learning
artificial intelligence
reinforcement learning
objective function
search space
dynamic programming
state variables
sequential decision making