Safe Reinforcement Learning via Confidence-Based Filters.
Sebastian CuriArmin LedererSandra HircheAndreas KrausePublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- state space
- confidence measure
- confidence level
- morphological filters
- reinforcement learning algorithms
- high confidence
- gabor filters
- temporal difference
- digital filters
- model free
- action selection
- image filtering
- optimal policy
- robotic control
- steerable filters
- temporal difference learning
- edge enhancement
- policy search
- order statistics
- low pass filter
- markov decision processes
- dynamic programming