Leveraging Factored Action Spaces for Efficient Offline Reinforcement Learning in Healthcare.
Shengpu TangMaggie MakarMichael W. SjodingFinale Doshi-VelezJenna WiensPublished in: CoRR (2023)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- continuous state
- state and action spaces
- real valued
- function approximation
- non stationary
- function approximators
- reinforcement learning methods
- multi agent
- optimal control
- reinforcement learning algorithms
- single agent
- sufficient conditions
- state action
- machine learning