ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learning.
Jasmina GajcinIvana DusparicPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- model free
- robotic control
- bayesian networks
- learning process
- state space
- information systems
- causal relations
- temporal difference
- learning problems
- multi agent reinforcement learning
- temporal difference learning
- causal relationships
- causal models
- optimal control
- real time
- markov decision processes
- optimal policy
- dynamic programming
- case study
- learning algorithm