Causal Explanation for Reinforcement Learning: Quantifying State and Temporal Importance

October 24, 2022 Β· Declared Dead Β· πŸ› Applied intelligence (Boston)

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Xiaoxiao Wang, Fanyu Meng, Xin Liu, Zhaodan Kong, Xin Chen arXiv ID 2210.13507 Category cs.AI: Artificial Intelligence Cross-listed cs.LG Citations 4 Venue Applied intelligence (Boston) Last Checked 4 months ago
Abstract
Explainability plays an increasingly important role in machine learning. Furthermore, humans view the world through a causal lens and thus prefer causal explanations over associational ones. Therefore, in this paper, we develop a causal explanation mechanism that quantifies the causal importance of states on actions and such importance over time. We also demonstrate the advantages of our mechanism over state-of-the-art associational methods in terms of RL policy explanation through a series of simulation studies, including crop irrigation, Blackjack, collision avoidance, and lunar lander.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence

Died the same way β€” πŸ‘» Ghosted