Reinforcement learning optimal control with semi-continuous reward function and fuzzy-rules networks for drug administration of cancer treatment.
Chidentree TreesatayapunAldo-Jonathan Muñoz-VázquezNaret SuyarojPublished in: Soft Comput. (2023)
Keyphrases
- optimal control
- fuzzy rules
- reinforcement learning
- reward function
- cancer treatment
- optimal control problems
- reinforcement learning algorithms
- markov decision processes
- fuzzy systems
- neuro fuzzy
- state space
- rule base
- action space
- membership functions
- dynamic programming
- fuzzy sets
- fuzzy logic
- inverse reinforcement learning
- fuzzy neural network
- optimal policy
- function approximation
- fuzzy model
- decision support
- infinite horizon
- markov decision process
- partially observable
- fuzzy control
- breast cancer
- fuzzy controller
- learning algorithm
- radiation therapy
- control law
- model free
- temporal difference
- control strategy
- image processing
- multi agent
- pattern recognition
- rough sets
- machine learning
- expert systems
- decision support system
- control policies
- network structure
- genetic algorithm