Generating reward functions using IRL towards individualized cancer screening.
Panayiotis PetousisSimon X. HanWilliam HsuAlex A. T. BuiPublished in: AIH@IJCAI (2018)
Keyphrases
- reward function
- inverse reinforcement learning
- markov decision processes
- reinforcement learning
- reinforcement learning algorithms
- state space
- cervical cancer
- multiple agents
- optimal policy
- partially observable
- transition probabilities
- state variables
- drug discovery
- breast cancer
- policy search
- markov decision process
- preference elicitation
- initially unknown
- state action
- simple examples
- markov decision problems