Safe Reinforcement Learning via Confidence-Based Filters.
Sebastian CuriArmin LedererSandra HircheAndreas KrausePublished in: CDC (2022)
Keyphrases
- reinforcement learning
- state space
- reinforcement learning algorithms
- high confidence
- markov decision processes
- function approximation
- multi agent
- model free
- robotic control
- confidence measure
- learning algorithm
- confidence level
- order statistics
- temporal difference
- action selection
- optimal policy
- dynamic programming
- edge detection
- supervised learning
- edge enhancement
- adaptive filtering
- median filter
- gabor filters
- digital filters
- learning process
- filter design
- band pass filters
- data mining
- confidence values
- low pass filter
- nonlinear filters
- bandpass
- filter responses
- morphological filters
- transfer learning
- learning problems
- learning classifier systems