Detection of Important States through an Iterative Q-value Algorithm for Explainable Reinforcement Learning.
Rudy MilaniMaximilian MollRenato De LeonePublished in: HICSS (2024)
Keyphrases
- detection algorithm
- k means
- dynamic programming
- learning algorithm
- cost function
- experimental evaluation
- preprocessing
- np hard
- reinforcement learning
- convergence rate
- optimal solution
- detection method
- computational cost
- least squares
- state variables
- times faster
- significant improvement
- expectation maximization
- search space
- monte carlo
- detection rate
- model free
- stochastic approximation
- machine learning
- high accuracy
- simulated annealing
- face detection
- lower bound
- objective function
- similarity measure
- line detection
- anti noise