Incorporating prior knowledge into Q-learning for drug delivery individualization.
Adam E. GawedaMehmet Kerem MüezzinogluGeorge R. AronoffAlfred A. JacobsJacek M. ZuradaMichael E. BrierPublished in: ICMLA (2005)
Keyphrases
- incorporating prior knowledge
- prior knowledge
- function approximation
- reinforcement learning
- cooperative
- learning algorithm
- multi agent
- model free
- state space
- learning rate
- action selection
- drug discovery
- multi agent reinforcement learning
- optimal policy
- stochastic approximation
- learning agent
- potential field
- td learning
- drug resistance