The paper introduces Temporal-Logic-based Causal Diagrams (TL-CDs) for reinforcement learning tasks that involve temporally extended goals. TL-CDs encode causal relationships among environmental properties, complementing deterministic finite automata that model rewards. By leveraging TL-CDs, the authors design an RL algorithm that can predict expected rewards early, leading to significantly reduced exploration and faster convergence to optimal policies.
By Yash Paliwal, Rajarshi Roy, Jean-Rapha\"el Gaglione, Nasim Baharisangari, Daniel Neider, Xiaoming Duan, Ufuk Topcu, Zhe Xu
arXiv:2606. 24160v1 Announce Type: new Abstract: Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i.
By Elias Bareinboim, Junzhe Zhang, Sanghack Lee
arXiv:2608. 13625v1 Announce Type: new Abstract: Signal temporal logic (STL) provides a formal language for specifying real-time properties of real-valued observations, along with a quantitative robustness score for monitoring satisfaction.
By Alper Kamil Bozkurt, Shangtong Zhang, Yuichi Motai
Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i. e.
arXiv:2607. 26336v1 Announce Type: new Abstract: In model-based reinforcement learning, world models exist as internal simulators, but their training often conflates statistical correlations with causal mechanisms.
By Jasorsi Ghosh
arXiv:2606. 29681v1 Announce Type: new Abstract: Probabilistic model checking for Markov decision processes (MDPs) provides quantitative guarantees, but often offers limited insight into why undesired outcomes occur.
By Ryohei Oura, Georgios Fainekos, Hideki Okamoto, Bardh Hoxha
arXiv:2603. 06946v2 Announce Type: replace Abstract: Many distributional quantities in reinforcement learning are intrinsically joint across actions, including distributions of gaps and probabilities of superiority.
By Ege C. Kaya, Mahsa Ghasemi, Abolfazl Hashemi
Probabilistic model checking for Markov decision processes (MDPs) provides quantitative guarantees, but often offers limited insight into why undesired outcomes occur. Probability-raising (PR) causality addresses this by identifying states whose visitation increases the probability of reaching designated states.
arXiv:2607. 16421v1 Announce Type: new Abstract: It has long been recognized that humans have the ability to switch between fast, reactive decision-making and slower, deliberative planning.
By Adam Labiosa, Josiah P. Hanna
arXiv:2607. 03177v1 Announce Type: cross Abstract: Traditional reinforcement learning (RL) for recovery in autonomous systems lacks causal understanding and generalizes poorly to novel failure scenarios.
By Safia Fatima, Kai Olav Ellefsen, Leon Moonen
arXiv:2608. 08743v1 Announce Type: cross Abstract: Reinforcement learning (RL) seeks to optimize sequential decisions to maximize population-level benefits over time.
By Jianhan Zhang, Jitao Wang, John D. Piette, Donglin Zeng, Chengchun Shi, Zhenke Wu
arXiv:2606. 16933v1 Announce Type: cross Abstract: Reinforcement learning (RL) systems often degrade when operating conditions differ from those previously encountered, reflecting distributional shifts in the underlying data-generating process.
By Ardianto Wibowo, Paulo E Santos, Amer Baghdadi, Matthew Stephenson, Karl Sammut, Jean-Philippe Diguet