Testing for Fault Diversity in Reinforcement Learning.
Quentin MazouniHelge SpiekerArnaud GotliebMathieu AcherPublished in: CoRR (2024)
Keyphrases
- error detection
- reinforcement learning
- learning algorithm
- fault model
- temporal difference
- model free
- markov decision processes
- temporal difference learning
- function approximation
- learning problems
- fault diagnosis
- test cases
- optimal policy
- state space
- dynamic programming
- neural network
- test set
- learning classifier systems
- software testing
- hidden markov models
- expert systems
- reinforcement learning methods
- decision making
- robotic control