Explainable Reinforcement Learning via a Causal World Model.
Zhongwei YuJingqing RuanDengpeng XingPublished in: CoRR (2023)
Keyphrases
- world model
- reinforcement learning
- vision system
- semantic interpretation
- function approximation
- markov decision processes
- state space
- learning algorithm
- causal relationships
- causal models
- optimal policy
- bayesian networks
- action selection
- model free
- temporal difference
- image processing
- machine learning
- causal networks
- reinforcement learning algorithms
- causal reasoning
- decision support system
- multi agent
- neural network
- directed acyclic graph
- dynamic programming
- expert systems
- training data
- database systems
- decision making
- action space
- computer vision
- databases