A reinforcement learning approach for finding optimal policy of adaptive radiation therapy considering uncertain tumor biological response.
Saba EbrahimiGino J. LimPublished in: Artif. Intell. Medicine (2021)
Keyphrases
- optimal policy
- reinforcement learning
- radiation therapy
- treatment planning
- normal tissue
- markov decision processes
- state space
- cancer treatment
- dynamic programming
- infinite horizon
- finite horizon
- state dependent
- long run
- ct images
- markov decision process
- markov decision problems
- average reward
- computer aided
- policy iteration
- bayesian reinforcement learning
- image guided
- reward function
- treatment plan
- control policies
- radiation dose
- prostate cancer
- function approximation
- model free
- decision making
- sufficient conditions
- cancer patients
- automated segmentation
- reinforcement learning algorithms
- imaging modalities
- ct scans
- temporal difference
- deformable registration
- medical images
- brain tumors
- partially observable markov decision processes