SAC-FACT: Soft Actor-Critic Reinforcement Learning for Counterfactual Explanations.
Fatima EzzeddineOmran AyoubDavide AndreolettiSilvia GiordanoPublished in: xAI (1) (2023)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- approximate dynamic programming
- reinforcement learning algorithms
- optimal control
- function approximation
- neuro fuzzy
- gradient method
- global optimization
- policy iteration
- model free
- policy gradient methods
- optimal policy
- linear program
- learning algorithm
- dynamic programming
- neural network
- learning problems
- multi agent
- average reward
- state space
- control problems
- supervised learning
- markov decision processes
- reinforcement learning methods
- adaptive control
- transfer learning
- machine learning
- natural actor critic