Offline reinforcement learning in high-dimensional stochastic environments.
Félicien HêcheOussama BarakatThibaut DesmettreTania MarxStephan Robert-NicoudPublished in: Neural Comput. Appl. (2024)
Keyphrases
- high dimensional
- reinforcement learning
- direct policy search
- stochastic approximation
- learning automata
- multi agent environments
- state space
- low dimensional
- real world
- reinforcement learning algorithms
- machine learning
- dimensionality reduction
- high dimensionality
- learning algorithm
- stochastic optimization
- model free
- function approximation
- monte carlo
- real time
- high dimensional data
- multi agent
- multi dimensional
- high dimensional problems
- variable selection
- data points
- policy search
- temporal difference learning
- similarity search
- control problems
- parameter space
- transfer learning
- nearest neighbor
- feature space
- similarity measure
- neural network