Automating reward function configuration for drug design.
Marius UrbonasTemitope AjileyePaul GainerDouglas PiresPublished in: CoRR (2023)
Keyphrases
- drug design
- reward function
- reinforcement learning
- inverse reinforcement learning
- state space
- markov decision processes
- optimal policy
- protein structure prediction
- protein protein interactions
- multiple agents
- quantitative structure activity
- drug discovery
- transition probabilities
- dynamic programming
- generative model
- data management