Safe reinforcement learning using risk mapping by similarity.
Jonathan Serrano CuevasEduardo F. MoralesPablo Hernandez-LealPublished in: Adapt. Behav. (2020)
Keyphrases
- reinforcement learning
- similarity measure
- function approximation
- distance function
- neural network
- markov decision processes
- machine learning
- learning algorithm
- model free
- distance measure
- similarity function
- multi agent reinforcement learning
- similarity metrics
- risk factors
- learning problems
- genetic algorithm
- optimal policy
- supervised learning
- state space
- robotic control
- markov decision process
- ontology mapping
- decision making
- similarity scores
- structural similarity
- temporal difference
- risk assessment
- optimal control
- edit distance
- semantic similarity
- distance metric