Explainable Reinforcement Learning via a Causal World Model.
Zhongwei YuJingqing RuanDengpeng XingPublished in: IJCAI (2023)
Keyphrases
- world model
- reinforcement learning
- vision system
- semantic interpretation
- function approximation
- model free
- causal models
- reinforcement learning algorithms
- state space
- causal relationships
- causal reasoning
- temporal difference
- markov decision processes
- bayesian networks
- optimal control
- learning algorithm
- causal discovery
- real time
- dynamic programming
- multi agent
- optimal policy
- knowledge based systems
- learning process
- information systems
- computer vision