Assessing Explainability in Reinforcement Learning.
Amber E. ZelvelderMarcus WestbergKary FrämlingPublished in: EXTRAAMAS@AAMAS (2021)
Keyphrases
- reinforcement learning
- markov decision processes
- function approximation
- control problems
- state space
- temporal difference
- reinforcement learning algorithms
- learning process
- optimal control
- transfer learning
- optimal policy
- action space
- function approximators
- temporal difference learning
- robotic control
- learning agent
- transition model
- database
- model free
- learning tasks
- control system
- multi agent
- objective function
- bayesian networks
- decision trees
- knowledge base
- decision making
- learning algorithm