IxDRL: A Novel Explainable Deep Reinforcement Learning Toolkit Based on Analyses of Interestingness.
Pedro SequeiraMelinda T. GervasioPublished in: xAI (1) (2023)
Keyphrases
- reinforcement learning
- function approximation
- model free
- association rules
- markov decision processes
- optimal policy
- state space
- machine learning
- learning process
- temporal difference
- interestingness measures
- learning problems
- reinforcement learning algorithms
- deep learning
- temporal difference learning
- policy search
- robotic control
- user defined
- dynamic programming
- learning algorithm
- pattern discovery
- radial basis function
- comparative analysis
- error analysis
- database
- classification rules
- learning capabilities
- learning environment
- action space
- data structure
- real world