Explanation-Guided Deep Reinforcement Learning for Trustworthy 6G RAN Slicing.
Farhad RezazadehHatim CherguiJosep Mangues-BafalluyPublished in: ICC Workshops (2023)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- state space
- learning algorithm
- model free
- direct policy search
- machine learning
- control problems
- dynamic programming
- markov decision processes
- multi agent
- transition model
- multi agent reinforcement learning
- temporal difference
- optimal policy
- causal explanation
- program slicing
- learning process
- deep learning
- database
- robotic control
- relational reinforcement learning
- description languages
- bayesian networks
- trust management
- real robot
- active learning
- data sets
- decision trees
- real world
- learning classifier systems
- optimal control
- supervised learning
- learning problems