f-Divergence Optimization for Task-Parameterized Learning from Demonstrations Algorithm.
Adrián PradosAlberto MendezGonzalo EspinozaNoelia FernandezRamón BarberPublished in: ICARSC (2024)
Keyphrases
- learning algorithm
- optimization algorithm
- cost function
- times faster
- np hard
- stochastic gradient descent
- optimization process
- worst case
- computational cost
- improved algorithm
- detection algorithm
- segmentation algorithm
- computational complexity
- linear programming
- incremental learning
- search space
- learning speed
- k means
- neural network
- similarity measure
- constrained optimization
- learning tasks
- learning phase
- optimization method
- matching algorithm
- preprocessing
- theoretical analysis
- supervised learning
- experimental evaluation
- dynamic programming
- combinatorial optimization
- particle swarm optimization
- high accuracy
- learning process
- significant improvement
- prior knowledge