Physics-informed reinforcement learning via probabilistic co-adjustment functions.
Nat WannawasA. Aldo FaisalPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- bayesian networks
- state space
- neural network
- generative model
- parametric family
- function approximation
- probabilistic model
- learning algorithm
- information systems
- optimal control
- temporal difference
- partially observable
- stochastic approximation
- machine learning
- computer science
- artificial neural networks
- real time
- data driven
- optimal policy
- case study
- reinforcement learning algorithms
- probability functions
- decision trees