Reinforcement learning based algorithm with Safety Handling and Risk Perception.
Suhas ShyamsundarTommaso MannucciErik-Jan van KampenPublished in: SSCI (2016)
Keyphrases
- dynamic programming
- reinforcement learning
- learning algorithm
- improved algorithm
- detection algorithm
- optimization algorithm
- experimental evaluation
- np hard
- optimal solution
- high accuracy
- particle swarm optimization
- k means
- cost function
- worst case
- theoretical analysis
- segmentation algorithm
- similarity measure
- expectation maximization
- neural network
- recognition algorithm
- convergence rate
- matching algorithm
- tree structure
- objective function
- computationally efficient
- computational complexity
- search algorithm
- significant improvement
- preprocessing