Optimal drug-dosing of cancer dynamics with fuzzy reinforcement learning and discontinuous reward function.
Chidentree TreesatayapunAldo-Jonathan Muñoz-VázquezPublished in: Eng. Appl. Artif. Intell. (2023)
Keyphrases
- reward function
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- initially unknown
- optimal policy
- competitive ratio
- partially observable
- dynamic programming
- state space
- inverse reinforcement learning
- control policies
- transition model
- average reward
- function approximation
- optimal control
- multiple agents
- hierarchical reinforcement learning
- dynamical systems
- fuzzy logic
- optimal solution
- minimax regret
- machine learning
- markov decision process
- learning agent
- fuzzy numbers
- state action
- approximate dynamic programming
- policy search
- learning algorithm
- transition probabilities
- control policy
- data mining