An advantage based policy transfer algorithm for reinforcement learning with metrics of transferability.
Md Ferdous AlamParinaz NaghizadehDavid J. HoelzlePublished in: CoRR (2023)
Keyphrases
- computational cost
- optimal solution
- learning algorithm
- experimental evaluation
- cost function
- reinforcement learning
- dynamic programming
- detection algorithm
- k means
- similarity measure
- times faster
- simulated annealing
- np hard
- feature selection
- recognition algorithm
- expectation maximization
- objective function
- search space
- preprocessing
- significant improvement
- neural network
- high accuracy
- evolutionary algorithm
- computational complexity
- convergence rate
- search algorithm
- policy gradient
- approximate dynamic programming
- policy search