Deep Reinforcement Learning Based Optimal Infinite-Horizon Control of Probabilistic Boolean Control Networks.

Jingjie Ni Fangfei Li Zheng-Guang Wu

Published in: CoRR (2023)

Keyphrases

optimal control
infinite horizon
reinforcement learning
dynamic programming
markov decision processes
control system
optimal policy
partially observable
single item
learning algorithm
state space
long run
single agent
finite horizon
control policy
control policies