Softmax and ε-greedy policies applied to process control
S Syafiie, F Tadeo, E Martinez - IFAC Proceedings Volumes, 2004 - Elsevier
Q-learning is a Reinforcement Learning method where the learner builds incrementally the
Q-function which estimates the future rewards for taking actions from a given state. This …
Q-function which estimates the future rewards for taking actions from a given state. This …
[PDF][PDF] Learning control applied to ph plant
S Syafiie, F Tadeo, E Martinez - … Symposium on Dynamics and Control of …, 2004 - nt.ntnu.no
This paper presents an experimental application of the reinforcement learning method on
process control. Reinforcement learning is a model-free technique based on learning how to …
process control. Reinforcement learning is a model-free technique based on learning how to …