Explainability of deep reinforcement learning algorithms in robotic domains by using Layer-wise Relevance Propagation.
Mehran TaghianShotaro MiwaYoshihiro MitsukaJohannes GüntherShadan GolestanOsmar R. ZaïanePublished in: Eng. Appl. Artif. Intell. (2024)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- state space
- model free
- markov decision processes
- reinforcement learning problems
- eligibility traces
- learning algorithm
- function approximation
- temporal difference
- reinforcement learning methods
- dynamic environments
- pairwise
- mobile robot
- complex domains
- policy search
- data mining
- optimal policy
- support vector machine svm
- monte carlo
- transfer learning
- markov chain