Optimization of oxygen system scheduling in hybrid action space based on deep reinforcement learning.
Lijuan LiXue YangShipin YangXiaowei XuPublished in: Comput. Chem. Eng. (2023)
Keyphrases
- action space
- reinforcement learning
- state space
- markov decision processes
- state and action spaces
- continuous state
- real valued
- control policies
- continuous state spaces
- action selection
- state action
- function approximation
- reinforcement learning methods
- markov decision process
- stochastic processes
- optimal policy
- machine learning
- partially observable
- single agent
- function approximators
- control problems
- probabilistic model
- reinforcement learning algorithms
- model free
- state variables
- supervised learning
- markov chain